Motion-Estimation.md

Motion Estimation

Title	Date	Abstract	Comment	CodeRepository
Impact of Temporal Delay on Radar-Inertial Odometry	2025-03-04	Show Accurate ego-motion estimation is a critical component of any autonomous system. Conventional ego-motion sensors, such as cameras and LiDARs, may be compromised in adverse environmental conditions, such as fog, heavy rain, or dust. Automotive radars, known for their robustness to such conditions, present themselves as complementary sensors or a promising alternative within the ego-motion estimation frameworks. In this paper we propose a novel Radar-Inertial Odometry (RIO) system that integrates an automotive radar and an inertial measurement unit. The key contribution is the integration of online temporal delay calibration within the factor graph optimization framework that compensates for potential time offsets between radar and IMU measurements. To validate the proposed approach we have conducted thorough experimental analysis on real-world radar and IMU data. The results show that, even without scan matching or target tracking, integration of online temporal calibration significantly reduces localization error compared to systems that disregard time synchronization, thus highlighting the important role of, often neglected, accurate temporal alignment in radar-based sensor fusion systems for autonomous navigation.		None
CAO-RONet: A Robust 4D Radar Odometry with Exploring More Information from Low-Quality Points	2025-03-03	Show Recently, 4D millimetre-wave radar exhibits more stable perception ability than LiDAR and camera under adverse conditions (e.g. rain and fog). However, low-quality radar points hinder its application, especially the odometry task that requires a dense and accurate matching. To fully explore the potential of 4D radar, we introduce a learning-based odometry framework, enabling robust ego-motion estimation from finite and uncertain geometry information. First, for sparse radar points, we propose a local completion to supplement missing structures and provide denser guideline for aligning two frames. Then, a context-aware association with a hierarchical structure flexibly matches points of different scales aided by feature similarity, and improves local matching consistency through correlation balancing. Finally, we present a window-based optimizer that uses historical priors to establish a coupling state estimation and correct errors of inter-frame matching. The superiority of our algorithm is confirmed on View-of-Delft dataset, achieving around a 50% performance improvement over previous approaches and delivering accuracy on par with LiDAR odometry. Our code will be available.	7 pages, 7 figures	None
DELTA: Dense Efficient Long-range 3D Tracking for any video	2025-02-28	Show Tracking dense 3D motion from monocular videos remains challenging, particularly when aiming for pixel-level precision over long sequences. We introduce DELTA, a novel method that efficiently tracks every pixel in 3D space, enabling accurate motion estimation across entire videos. Our approach leverages a joint global-local attention mechanism for reduced-resolution tracking, followed by a transformer-based upsampler to achieve high-resolution predictions. Unlike existing methods, which are limited by computational inefficiency or sparse tracking, DELTA delivers dense 3D tracking at scale, running over 8x faster than previous methods while achieving state-of-the-art accuracy. Furthermore, we explore the impact of depth representation on tracking performance and identify log-depth as the optimal choice. Extensive experiments demonstrate the superiority of DELTA on multiple benchmarks, achieving new state-of-the-art results in both 2D and 3D dense tracking tasks. Our method provides a robust solution for applications requiring fine-grained, long-term motion tracking in 3D space.	ICLR ... ICLR 2025. Project Page: https://snap-research.github.io/DELTA/	Code Link
ORB-SfMLearner: ORB-Guided Self-supervised Visual Odometry with Selective Online Adaptation	2025-02-24	Show Deep visual odometry, despite extensive research, still faces limitations in accuracy and generalizability that prevent its broader application. To address these challenges, we propose an Oriented FAST and Rotated BRIEF (ORB)-guided visual odometry with selective online adaptation named ORB-SfMLearner. We present a novel use of ORB features for learning-based ego-motion estimation, leading to more robust and accurate results. We also introduce the cross-attention mechanism to enhance the explainability of PoseNet and have revealed that driving direction of the vehicle can be explained through the attention weights. To improve generalizability, our selective online adaptation allows the network to rapidly and selectively adjust to the optimal parameters across different domains. Experimental results on KITTI and vKITTI datasets show that our method outperforms previous state-of-the-art deep visual odometry methods in terms of ego-motion accuracy and generalizability.	Accep... Accepted to ICRA 2025; Project page: https://www.neiljin.site/projects/orbsfm/	None
Active Illumination for Visual Ego-Motion Estimation in the Dark	2025-02-19	Show Visual Odometry (VO) and Visual SLAM (V-SLAM) systems often struggle in low-light and dark environments due to the lack of robust visual features. In this paper, we propose a novel active illumination framework to enhance the performance of VO and V-SLAM algorithms in these challenging conditions. The developed approach dynamically controls a moving light source to illuminate highly textured areas, thereby improving feature extraction and tracking. Specifically, a detector block, which incorporates a deep learning-based enhancing network, identifies regions with relevant features. Then, a pan-tilt controller is responsible for guiding the light beam toward these areas, so that to provide information-rich images to the ego-motion estimation algorithm. Experimental results on a real robotic platform demonstrate the effectiveness of the proposed method, showing a reduction in the pose estimation error up to 75% with respect to a traditional fixed lighting technique.		None
DynoSAM: Open-Source Smoothing and Mapping Framework for Dynamic SLAM	2025-02-14	Show Traditional Visual Simultaneous Localization and Mapping (vSLAM) systems focus solely on static scene structures, overlooking dynamic elements in the environment. Although effective for accurate visual odometry in complex scenarios, these methods discard crucial information about moving objects. By incorporating this information into a Dynamic SLAM framework, the motion of dynamic entities can be estimated, enhancing navigation whilst ensuring accurate localization. However, the fundamental formulation of Dynamic SLAM remains an open challenge, with no consensus on the optimal approach for accurate motion estimation within a SLAM pipeline. Therefore, we developed DynoSAM, an open-source framework for Dynamic SLAM that enables the efficient implementation, testing, and comparison of various Dynamic SLAM optimization formulations. DynoSAM integrates static and dynamic measurements into a unified optimization problem solved using factor graphs, simultaneously estimating camera poses, static scene, object motion or poses, and object structures. We evaluate DynoSAM across diverse simulated and real-world datasets, achieving state-of-the-art motion estimation in indoor and outdoor environments, with substantial improvements over existing systems. Additionally, we demonstrate DynoSAM utility in downstream applications, including 3D reconstruction of dynamic scenes and trajectory prediction, thereby showcasing potential for advancing dynamic object-aware SLAM systems. DynoSAM is open-sourced at https://github.com/ACFR-RPG/DynOSAM.	20 pa... 20 pages, 10 figures. Submitted to T-RO Visual SLAM SI 2025	Code Link
A Cooperative Bearing-Rate Approach for Observability-Enhanced Target Motion Estimation	2025-02-12	Show Vision-based target motion estimation is a fundamental problem in many robotic tasks. The existing methods have the limitation of low observability and, hence, face challenges in tracking highly maneuverable targets. Motivated by the aerial target pursuit task where a target may maneuver in 3D space, this paper studies how to further enhance observability by incorporating the \emph{bearing rate} information that has not been well explored in the literature. The main contribution of this paper is to propose a new cooperative estimator called STT-R (Spatial-Temporal Triangulation with bearing Rate), which is designed under the framework of distributed recursive least squares. This theoretical result is further verified by numerical simulation and real-world experiments. It is shown that the proposed STT-R algorithm can effectively generate more accurate estimations and effectively reduce the lag in velocity estimation, enabling tracking of more maneuverable targets.	accep... accepted by icra 2025	None
Optimal Spatial-Temporal Triangulation for Bearing-Only Cooperative Motion Estimation	2025-02-12	Show Vision-based cooperative motion estimation is an important problem for many multi-robot systems such as cooperative aerial target pursuit. This problem can be formulated as bearing-only cooperative motion estimation, where the visual measurement is modeled as a bearing vector pointing from the camera to the target. The conventional approaches for bearing-only cooperative estimation are mainly based on the framework distributed Kalman filtering (DKF). In this paper, we propose a new optimal bearing-only cooperative estimation algorithm, named spatial-temporal triangulation, based on the method of distributed recursive least squares, which provides a more flexible framework for designing distributed estimators than DKF. The design of the algorithm fully incorporates all the available information and the specific triangulation geometric constraint. As a result, the algorithm has superior estimation performance than the state-of-the-art DKF algorithms in terms of both accuracy and convergence speed as verified by numerical simulation. We rigorously prove the exponential convergence of the proposed algorithm. Moreover, to verify the effectiveness of the proposed algorithm under practical challenging conditions, we develop a vision-based cooperative aerial target pursuit system, which is the first of such fully autonomous systems so far to the best of our knowledge.	accep... accepted by Automatica	None
A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision	2025-02-11	Show Omnidirectional image (ODI) data is captured with a field-of-view of 360x180, which is much wider than the pinhole cameras and captures richer surrounding environment details than the conventional perspective images. In recent years, the availability of customer-level 360 cameras has made omnidirectional vision more popular, and the advance of deep learning (DL) has significantly sparked its research and applications. This paper presents a systematic and comprehensive review and analysis of the recent progress of DL for omnidirectional vision. It delineates the distinct challenges and complexities encountered in applying DL to omnidirectional images as opposed to traditional perspective imagery. Our work covers four main contents: (i) A thorough introduction to the principles of omnidirectional imaging and commonly explored projections of ODI; (ii) A methodical review of varied representation learning approaches tailored for ODI; (iii) An in-depth investigation of optimization strategies specific to omnidirectional vision; (iv) A structural and hierarchical taxonomy of the DL methods for the representative omnidirectional vision tasks, from visual enhancement (e.g., image generation and super-resolution) to 3D geometry and motion estimation (e.g., depth and optical flow estimation), alongside the discussions on emergent research directions; (v) An overview of cutting-edge applications (e.g., autonomous driving and virtual reality), coupled with a critical discussion on prevailing challenges and open questions, to trigger more research in the community.	37 pa... 37 pages, 24 figures, accepted by IJCV	None
FreeCap: Hybrid Calibration-Free Motion Capture in Open Environments	2025-02-10	Show We propose a novel hybrid calibration-free method FreeCap to accurately capture global multi-person motions in open environments. Our system combines a single LiDAR with expandable moving cameras, allowing for flexible and precise motion estimation in a unified world coordinate. In particular, We introduce a local-to-global pose-aware cross-sensor human-matching module that predicts the alignment among each sensor, even in the absence of calibration. Additionally, our coarse-to-fine sensor-expandable pose optimizer further optimizes the 3D human key points and the alignments, it is also capable of incorporating additional cameras to enhance accuracy. Extensive experiments on Human-M3 and FreeMotion datasets demonstrate that our method significantly outperforms state-of-the-art single-modal methods, offering an expandable and efficient solution for multi-person motion capture across various applications.		None
Enhancing Free-hand 3D Photoacoustic and Ultrasound Reconstruction using Deep Learning	2025-02-05	Show This study introduces a motion-based learning network with a global-local self-attention module (MoGLo-Net) to enhance 3D reconstruction in handheld photoacoustic and ultrasound (PAUS) imaging. Standard PAUS imaging is often limited by a narrow field of view and the inability to effectively visualize complex 3D structures. The 3D freehand technique, which aligns sequential 2D images for 3D reconstruction, faces significant challenges in accurate motion estimation without relying on external positional sensors. MoGLo-Net addresses these limitations through an innovative adaptation of the self-attention mechanism, which effectively exploits the critical regions, such as fully-developed speckle area or high-echogenic tissue area within successive ultrasound images to accurately estimate motion parameters. This facilitates the extraction of intricate features from individual frames. Additionally, we designed a patch-wise correlation operation to generate a correlation volume that is highly correlated with the scanning motion. A custom loss function was also developed to ensure robust learning with minimized bias, leveraging the characteristics of the motion parameters. Experimental evaluations demonstrated that MoGLo-Net surpasses current state-of-the-art methods in both quantitative and qualitative performance metrics. Furthermore, we expanded the application of 3D reconstruction technology beyond simple B-mode ultrasound volumes to incorporate Doppler ultrasound and photoacoustic imaging, enabling 3D visualization of vasculature. The source code for this study is publicly available at: https://github.com/guhong3648/US3D		Code Link
Low Resource Video Super-resolution using Memory and Residual Deformable Convolutions	2025-02-03	Show Transformer-based video super-resolution (VSR) models have set new benchmarks in recent years, but their substantial computational demands make most of them unsuitable for deployment on resource-constrained devices. Achieving a balance between model complexity and output quality remains a formidable challenge in VSR. Although lightweight models have been introduced to address this issue, they often struggle to deliver state-of-the-art performance. We propose a novel lightweight, parameter-efficient deep residual deformable convolution network for VSR. Unlike prior methods, our model enhances feature utilization through residual connections and employs deformable convolution for precise frame alignment, addressing motion dynamics effectively. Furthermore, we introduce a single memory tensor to capture information accrued from the past frames and improve motion estimation across frames. This design enables an efficient balance between computational cost and reconstruction quality. With just 2.3 million parameters, our model achieves state-of-the-art SSIM of 0.9175 on the REDS4 dataset, surpassing existing lightweight and many heavy models in both accuracy and resource efficiency. Architectural insights from our model pave the way for real-time VSR on streaming data.		None
Efficient Video Neural Network Processing Based on Motion Estimation	2025-01-25	Show Video neural network (VNN) processing using the conventional pipeline first converts Bayer video information into human understandable RGB videos using image signal processing (ISP) on a pixel by pixel basis. Then, VNN processing is performed on a frame by frame basis. Both ISP and VNN are computationally expensive with high power consumption and latency. In this paper, we propose an efficient VNN processing framework. Instead of using ISP, computer vision tasks are directly accomplished using Bayer pattern information. To accelerate VNN processing, motion estimation is introduced to find temporal redundancies in input video data so as to avoid repeated and unnecessary computations. Experiments show greater than 67% computation reduction, while maintaining computer vision task accuracy for typical computer vision tasks and data sets.		None
Scalable Benchmarking and Robust Learning for Noise-Free Ego-Motion and 3D Reconstruction from Noisy Video	2025-01-24	Show We aim to redefine robust ego-motion estimation and photorealistic 3D reconstruction by addressing a critical limitation: the reliance on noise-free data in existing models. While such sanitized conditions simplify evaluation, they fail to capture the unpredictable, noisy complexities of real-world environments. Dynamic motion, sensor imperfections, and synchronization perturbations lead to sharp performance declines when these models are deployed in practice, revealing an urgent need for frameworks that embrace and excel under real-world noise. To bridge this gap, we tackle three core challenges: scalable data generation, comprehensive benchmarking, and model robustness enhancement. First, we introduce a scalable noisy data synthesis pipeline that generates diverse datasets simulating complex motion, sensor imperfections, and synchronization errors. Second, we leverage this pipeline to create Robust-Ego3D, a benchmark rigorously designed to expose noise-induced performance degradation, highlighting the limitations of current learning-based methods in ego-motion accuracy and 3D reconstruction quality. Third, we propose Correspondence-guided Gaussian Splatting (CorrGS), a novel test-time adaptation method that progressively refines an internal clean 3D representation by aligning noisy observations with rendered RGB-D frames from clean 3D map, enhancing geometric alignment and appearance restoration through visual correspondence. Extensive experiments on synthetic and real-world data demonstrate that CorrGS consistently outperforms prior state-of-the-art methods, particularly in scenarios involving rapid motion and dynamic illumination.	Accep... Accepted by ICLR 2025; 92 Pages; Project Repo: https://github.com/Xiaohao-Xu/SLAM-under-Perturbation. arXiv admin note: substantial text overlap with arXiv:2406.16850	Code Link
Efficient Dynamic Image Reconstruction with motion estimation	2025-01-21	Show Dynamic inverse problems are challenging to solve due to the need to identify and incorporate appropriate regularization in both space and time. Moreover, the very large scale nature of such problems in practice presents an enormous computational challenge. In this work, in addition to the use of edge-enhancing regularization of spatial features, we propose a new regularization method that incorporates a temporal model that estimates the motion of objects in time. In particular, we consider the optical flow model that simultaneously estimates the motion and provides an approximation for the desired image, and we incorporate this information into the cost functional as an additional form of temporal regularization. We propose a computationally efficient algorithm to solve the jointly regularized problem that leverages a generalized Krylov subspace method. We illustrate the effectiveness of the prescribed approach on a wide range of numerical experiments, including limited angle and single-shot computerized tomography.	27 pa... 27 pages, 6 figures, 5 tables	None
TOFFE -- Temporally-binned Object Flow from Events for High-speed and Energy-Efficient Object Detection and Tracking	2025-01-21	Show Object detection and tracking is an essential perception task for enabling fully autonomous navigation in robotic systems. Edge robot systems such as small drones need to execute complex maneuvers at high-speeds with limited resources, which places strict constraints on the underlying algorithms and hardware. Traditionally, frame-based cameras are used for vision-based perception due to their rich spatial information and simplified synchronous sensing capabilities. However, obtaining detailed information across frames incurs high energy consumption and may not even be required. In addition, their low temporal resolution renders them ineffective in high-speed motion scenarios. Event-based cameras offer a biologically-inspired solution to this by capturing only changes in intensity levels at exceptionally high temporal resolution and low power consumption, making them ideal for high-speed motion scenarios. However, their asynchronous and sparse outputs are not natively suitable with conventional deep learning methods. In this work, we propose TOFFE, a lightweight hybrid framework for performing event-based object motion estimation (including pose, direction, and speed estimation), referred to as Object Flow. TOFFE integrates bio-inspired Spiking Neural Networks (SNNs) and conventional Analog Neural Networks (ANNs), to efficiently process events at high temporal resolutions while being simple to train. Additionally, we present a novel event-based synthetic dataset involving high-speed object motion to train TOFFE. Our experimental results show that TOFFE achieves 5.7x/8.3x reduction in energy consumption and 4.6x/5.8x reduction in latency on edge GPU(Jetson TX2)/hybrid hardware(Loihi-2 and Jetson TX2), compared to previous event-based object detection baselines.	8 pag... 8 pages, 6 figures, 4 tables	None
Event-based vision for egomotion estimation using precise event timing	2025-01-20	Show Egomotion estimation is crucial for applications such as autonomous navigation and robotics, where accurate and real-time motion tracking is required. However, traditional methods relying on inertial sensors are highly sensitive to external conditions, and suffer from drifts leading to large inaccuracies over long distances. Vision-based methods, particularly those utilising event-based vision sensors, provide an efficient alternative by capturing data only when changes are perceived in the scene. This approach minimises power consumption while delivering high-speed, low-latency feedback. In this work, we propose a fully event-based pipeline for egomotion estimation that processes the event stream directly within the event-based domain. This method eliminates the need for frame-based intermediaries, allowing for low-latency and energy-efficient motion estimation. We construct a shallow spiking neural network using a synaptic gating mechanism to convert precise event timing into bursts of spikes. These spikes encode local optical flow velocities, and the network provides an event-based readout of egomotion. We evaluate the network's performance on a dedicated chip, demonstrating strong potential for low-latency, low-power motion estimation. Additionally, simulations of larger networks show that the system achieves state-of-the-art accuracy in egomotion estimation tasks with event-based cameras, making it a promising solution for real-time, power-constrained robotics applications.	10 pa... 10 pages, 7 figures. Supplementary material: 4 pages, 1 figure	None
CorrDiff: Adaptive Delay-aware Detector with Temporal Cue Inputs for Real-time Object Detection	2025-01-09	Show Real-time object detection takes an essential part in the decision-making process of numerous real-world applications, including collision avoidance and path planning in autonomous driving systems. This paper presents a novel real-time streaming perception method named CorrDiff, designed to tackle the challenge of delays in real-time detection systems. The main contribution of CorrDiff lies in its adaptive delay-aware detector, which is able to utilize runtime-estimated temporal cues to predict objects' locations for multiple future frames, and selectively produce predictions that matches real-world time, effectively compensating for any communication and computational delays. The proposed model outperforms current state-of-the-art methods by leveraging motion estimation and feature enhancement, both for 1) single-frame detection for the current frame or the next frame, in terms of the metric mAP, and 2) the prediction for (multiple) future frame(s), in terms of the metric sAP (The sAP metric is to evaluate object detection algorithms in streaming scenarios, factoring in both latency and accuracy). It demonstrates robust performance across a range of devices, from powerful Tesla V100 to modest RTX 2080Ti, achieving the highest level of perceptual accuracy on all platforms. Unlike most state-of-the-art methods that struggle to complete computation within a single frame on less powerful devices, CorrDiff meets the stringent real-time processing requirements on all kinds of devices. The experimental results emphasize the system's adaptability and its potential to significantly improve the safety and reliability for many real-world systems, such as autonomous driving. Our code is completely open-sourced and is available at https://anonymous.4open.science/r/CorrDiff.	Submi... Submitted to IEEE JSAC Special Issue: Intelligent Communications for Real-Time Computer Vision (Comm4CV)	None
NextStop: An Improved Tracker For Panoptic LIDAR Segmentation Data	2025-01-08	Show 4D panoptic LiDAR segmentation is essential for scene understanding in autonomous driving and robotics ,combining semantic and instance segmentation with temporal consistency.Current methods, like 4D-PLS and 4D-STOP, use a tracking-by-detection methodology, employing deep learning networks to perform semantic and instance segmentation on each frame. To maintain temporal consistency, large-size instances detected in the current frame are compared and associated with instances within a temporal window that includes the current and preceding frames. However, their reliance on short-term instance detection, lack of motion estimation, and exclusion of small-sized instances lead to frequent identity switches and reduced tracking performance. We address these issues with the NextStop1 tracker, which integrates Kalman filter-based motion estimation, data association, and lifespan management, along with a tracklet state concept to improve prioritization. Evaluated using the LiDAR Segmentation and Tracking Quality (LSTQ) metric on the SemanticKITTI validation set, NextStop demonstrated enhanced tracking performance, particularly for small-sized objects like people and bicyclists, with fewer ID switches, earlier tracking initiation, and improved reliability in complex environments. The source code is available at https://github.com/AIROTAU/NextStopTracker		Code Link
Joint Optimization for 4D Human-Scene Reconstruction in the Wild	2025-01-04	Show Reconstructing human motion and its surrounding environment is crucial for understanding human-scene interaction and predicting human movements in the scene. While much progress has been made in capturing human-scene interaction in constrained environments, those prior methods can hardly reconstruct the natural and diverse human motion and scene context from web videos. In this work, we propose JOSH, a novel optimization-based method for 4D human-scene reconstruction in the wild from monocular videos. JOSH uses techniques in both dense scene reconstruction and human mesh recovery as initialization, and then it leverages the human-scene contact constraints to jointly optimize the scene, the camera poses, and the human motion. Experiment results show JOSH achieves better results on both global human motion estimation and dense scene reconstruction by joint optimization of scene geometry and human motion. We further design a more efficient model, JOSH3R, and directly train it with pseudo-labels from web videos. JOSH3R outperforms other optimization-free methods by only training with labels predicted from JOSH, further demonstrating its accuracy and generalization ability.	Proje... Project Page: https://genforce.github.io/JOSH/	Code Link
Universal Online Temporal Calibration for Optimization-based Visual-Inertial Navigation Systems	2025-01-03	Show 6-Degree of Freedom (6DoF) motion estimation with a combination of visual and inertial sensors is a growing area with numerous real-world applications. However, precise calibration of the time offset between these two sensor types is a prerequisite for accurate and robust tracking. To address this, we propose a universal online temporal calibration strategy for optimization-based visual-inertial navigation systems. Technically, we incorporate the time offset td as a state parameter in the optimization residual model to align the IMU state to the corresponding image timestamp using td, angular velocity and translational velocity. This allows the temporal misalignment td to be optimized alongside other tracking states during the process. As our method only modifies the structure of the residual model, it can be applied to various optimization-based frameworks with different tracking frontends. We evaluate our calibration method with both EuRoC and simulation data and extensive experiments demonstrate that our approach provides more accurate time offset estimation and faster convergence, particularly in the presence of noisy sensor data.	7 pages	None
AR4D: Autoregressive 4D Generation from Monocular Videos	2025-01-03	Show Recent advancements in generative models have ignited substantial interest in dynamic 3D content creation (\ie, 4D generation). Existing approaches primarily rely on Score Distillation Sampling (SDS) to infer novel-view videos, typically leading to issues such as limited diversity, spatial-temporal inconsistency and poor prompt alignment, due to the inherent randomness of SDS. To tackle these problems, we propose AR4D, a novel paradigm for SDS-free 4D generation. Specifically, our paradigm consists of three stages. To begin with, for a monocular video that is either generated or captured, we first utilize pre-trained expert models to create a 3D representation of the first frame, which is further fine-tuned to serve as the canonical space. Subsequently, motivated by the fact that videos happen naturally in an autoregressive manner, we propose to generate each frame's 3D representation based on its previous frame's representation, as this autoregressive generation manner can facilitate more accurate geometry and motion estimation. Meanwhile, to prevent overfitting during this process, we introduce a progressive view sampling strategy, utilizing priors from pre-trained large-scale 3D reconstruction models. To avoid appearance drift introduced by autoregressive generation, we further incorporate a refinement stage based on a global deformation field and the geometry of each frame's 3D representation. Extensive experiments have demonstrated that AR4D can achieve state-of-the-art 4D generation without SDS, delivering greater diversity, improved spatial-temporal consistency, and better alignment with input prompts.	TL;DR... TL;DR: We present a novel method for 4D generation from monocular videos without relying on SDS, delivering greater diversity, improved spatial-temporal consistency, and better alignment with input prompts. Project page: https://hanxinzhu-lab.github.io/AR4D/	Code Link
BiM-VFI: directional Motion Field-Guided Frame Interpolation for Video with Non-uniform Motions	2024-12-29	Show Existing Video Frame interpolation (VFI) models tend to suffer from time-to-location ambiguity when trained with video of non-uniform motions, such as accelerating, decelerating, and changing directions, which often yield blurred interpolated frames. In this paper, we propose (i) a novel motion description map, Bidirectional Motion field (BiM), to effectively describe non-uniform motions; (ii) a BiM-guided Flow Net (BiMFN) with Content-Aware Upsampling Network (CAUN) for precise optical flow estimation; and (iii) Knowledge Distillation for VFI-centric Flow supervision (KDVCF) to supervise the motion estimation of VFI model with VFI-centric teacher flows. The proposed VFI is called a Bidirectional Motion field-guided VFI (BiM-VFI) model. Extensive experiments show that our BiM-VFI model significantly surpasses the recent state-of-the-art VFI methods by 26% and 45% improvements in LPIPS and STLPIPS respectively, yielding interpolated frames with much fewer blurs at arbitrary time instances.	The l... The last two authors are co-corresponding authors	None
V$^2$-SfMLearner: Learning Monocular Depth and Ego-motion for Multimodal Wireless Capsule Endoscopy	2024-12-23	Show Deep learning can predict depth maps and capsule ego-motion from capsule endoscopy videos, aiding in 3D scene reconstruction and lesion localization. However, the collisions of the capsule endoscopies within the gastrointestinal tract cause vibration perturbations in the training data. Existing solutions focus solely on vision-based processing, neglecting other auxiliary signals like vibrations that could reduce noise and improve performance. Therefore, we propose V$^2$-SfMLearner, a multimodal approach integrating vibration signals into vision-based depth and capsule motion estimation for monocular capsule endoscopy. We construct a multimodal capsule endoscopy dataset containing vibration and visual signals, and our artificial intelligence solution develops an unsupervised method using vision-vibration signals, effectively eliminating vibration perturbations through multimodal learning. Specifically, we carefully design a vibration network branch and a Fourier fusion module, to detect and mitigate vibration noises. The fusion framework is compatible with popular vision-only algorithms. Extensive validation on the multimodal dataset demonstrates superior performance and robustness against vision-only algorithms. Without the need for large external equipment, our V$^2$-SfMLearner has the potential for integration into clinical capsule robots, providing real-time and dependable digestive examination tools. The findings show promise for practical implementation in clinical settings, enhancing the diagnostic capabilities of doctors.	To ap... To appear in IEEE Transactions on Automation Science and Engineering (IEEE TASE)	None
A Plug-and-Play Physical Motion Restoration Approach for In-the-Wild High-Difficulty Motions	2024-12-23	Show Extracting physically plausible 3D human motion from videos is a critical task. Although existing simulation-based motion imitation methods can enhance the physical quality of daily motions estimated from monocular video capture, extending this capability to high-difficulty motions remains an open challenge. This can be attributed to some flawed motion clips in video-based motion capture results and the inherent complexity in modeling high-difficulty motions. Therefore, sensing the advantage of segmentation in localizing human body, we introduce a mask-based motion correction module (MCM) that leverages motion context and video mask to repair flawed motions, producing imitation-friendly motions; and propose a physics-based motion transfer module (PTM), which employs a pretrain and adapt approach for motion imitation, improving physical plausibility with the ability to handle in-the-wild and challenging motions. Our approach is designed as a plug-and-play module to physically refine the video motion capture results, including high-difficulty in-the-wild motions. Finally, to validate our approach, we collected a challenging in-the-wild test set to establish a benchmark, and our method has demonstrated effectiveness on both the new benchmark and existing public datasets.https://physicalmotionrestoration.github.io		None
CompactFlowNet: Efficient Real-time Optical Flow Estimation on Mobile Devices	2024-12-17	Show We present CompactFlowNet, the first real-time mobile neural network for optical flow prediction, which involves determining the displacement of each pixel in an initial frame relative to the corresponding pixel in a subsequent frame. Optical flow serves as a fundamental building block for various video-related tasks, such as video restoration, motion estimation, video stabilization, object tracking, action recognition, and video generation. While current state-of-the-art methods prioritize accuracy, they often overlook constraints regarding speed and memory usage. Existing light models typically focus on reducing size but still exhibit high latency, compromise significantly on quality, or are optimized for high-performance GPUs, resulting in sub-optimal performance on mobile devices. This study aims to develop a mobile-optimized optical flow model by proposing a novel mobile device-compatible architecture, as well as enhancements to the training pipeline, which optimize the model for reduced weight, low memory utilization, and increased speed while maintaining minimal error. Our approach demonstrates superior or comparable performance to the state-of-the-art lightweight models on the challenging KITTI and Sintel benchmarks. Furthermore, it attains a significantly accelerated inference speed, thereby yielding real-time operational efficiency on the iPhone 8, while surpassing real-time performance levels on more advanced mobile devices.		None
Estimating Body and Hand Motion in an Ego-sensed World	2024-12-17	Show We present EgoAllo, a system for human motion estimation from a head-mounted device. Using only egocentric SLAM poses and images, EgoAllo guides sampling from a conditional diffusion model to estimate 3D body pose, height, and hand parameters that capture a device wearer's actions in the allocentric coordinate frame of the scene. To achieve this, our key insight is in representation: we propose spatial and temporal invariance criteria for improving model performance, from which we derive a head motion conditioning parameterization that improves estimation by up to 18%. We also show how the bodies estimated by our system can improve hand estimation: the resulting kinematic and temporal constraints can reduce world-frame errors in single-frame estimates by 40%. Project page: https://egoallo.github.io/	Proje... Project page: https://egoallo.github.io/	None
EnvPoser: Environment-aware Realistic Human Motion Estimation from Sparse Observations with Uncertainty Modeling	2024-12-13	Show Estimating full-body motion using the tracking signals of head and hands from VR devices holds great potential for various applications. However, the sparsity and unique distribution of observations present a significant challenge, resulting in an ill-posed problem with multiple feasible solutions (i.e., hypotheses). This amplifies uncertainty and ambiguity in full-body motion estimation, especially for the lower-body joints. Therefore, we propose a new method, EnvPoser, that employs a two-stage framework to perform full-body motion estimation using sparse tracking signals and pre-scanned environment from VR devices. EnvPoser models the multi-hypothesis nature of human motion through an uncertainty-aware estimation module in the first stage. In the second stage, we refine these multi-hypothesis estimates by integrating semantic and geometric environmental constraints, ensuring that the final motion estimation aligns realistically with both the environmental context and physical interactions. Qualitative and quantitative experiments on two public datasets demonstrate that our method achieves state-of-the-art performance, highlighting significant improvements in human motion estimation within motion-environment interaction scenarios.		None
MAC-Ego3D: Multi-Agent Gaussian Consensus for Real-Time Collaborative Ego-Motion and Photorealistic 3D Reconstruction	2024-12-12	Show Real-time multi-agent collaboration for ego-motion estimation and high-fidelity 3D reconstruction is vital for scalable spatial intelligence. However, traditional methods produce sparse, low-detail maps, while recent dense mapping approaches struggle with high latency. To overcome these challenges, we present MAC-Ego3D, a novel framework for real-time collaborative photorealistic 3D reconstruction via Multi-Agent Gaussian Consensus. MAC-Ego3D enables agents to independently construct, align, and iteratively refine local maps using a unified Gaussian splat representation. Through Intra-Agent Gaussian Consensus, it enforces spatial coherence among neighboring Gaussian splats within an agent. For global alignment, parallelized Inter-Agent Gaussian Consensus, which asynchronously aligns and optimizes local maps by regularizing multi-agent Gaussian splats, seamlessly integrates them into a high-fidelity 3D model. Leveraging Gaussian primitives, MAC-Ego3D supports efficient RGB-D rendering, enabling rapid inter-agent Gaussian association and alignment. MAC-Ego3D bridges local precision and global coherence, delivering higher efficiency, largely reducing localization error, and improving mapping fidelity. It establishes a new SOTA on synthetic and real-world benchmarks, achieving a 15x increase in inference speed, order-of-magnitude reductions in ego-motion estimation error for partial cases, and RGB PSNR gains of 4 to 10 dB. Our code will be made publicly available at https://github.com/Xiaohao-Xu/MAC-Ego3D .	27 pages, 25 figures	Code Link
OmniDrag: Enabling Motion Control for Omnidirectional Image-to-Video Generation	2024-12-12	Show As virtual reality gains popularity, the demand for controllable creation of immersive and dynamic omnidirectional videos (ODVs) is increasing. While previous text-to-ODV generation methods achieve impressive results, they struggle with content inaccuracies and inconsistencies due to reliance solely on textual inputs. Although recent motion control techniques provide fine-grained control for video generation, directly applying these methods to ODVs often results in spatial distortion and unsatisfactory performance, especially with complex spherical motions. To tackle these challenges, we propose OmniDrag, the first approach enabling both scene- and object-level motion control for accurate, high-quality omnidirectional image-to-video generation. Building on pretrained video diffusion models, we introduce an omnidirectional control module, which is jointly fine-tuned with temporal attention layers to effectively handle complex spherical motion. In addition, we develop a novel spherical motion estimator that accurately extracts motion-control signals and allows users to perform drag-style ODV generation by simply drawing handle and target points. We also present a new dataset, named Move360, addressing the scarcity of ODV data with large scene and object motions. Experiments demonstrate the significant superiority of OmniDrag in achieving holistic scene-level and fine-grained object-level control for ODV generation. The project page is available at https://lwq20020127.github.io/OmniDrag.		Code Link
Humans as Checkerboards: Calibrating Camera Motion Scale for World-Coordinate Human Mesh Recovery	2024-12-12	Show Accurate camera motion estimation is essential for recovering global human motion in world coordinates from RGB video inputs. SLAM is widely used for estimating camera trajectory and point cloud, but monocular SLAM does so only up to an unknown scale factor. Previous works estimate the scale factor through optimization, but this is unreliable and time-consuming. This paper presents an optimization-free scale calibration framework, Human as Checkerboard (HAC). HAC innovatively leverages the human body predicted by human mesh recovery model as a calibration reference. Specifically, it uses the absolute depth of human-scene contact joints as references to calibrate the corresponding relative scene depth from SLAM. HAC benefits from geometric priors encoded in human mesh recovery models to estimate the SLAM scale and achieves precise global human motion estimation. Simple yet powerful, our method sets a new state-of-the-art performance for global human mesh estimation tasks, reducing motion errors by 50% over prior local-to-global methods while using 100$\times$ less inference time than optimization-based methods. Project page: https://martayang.github.io/HAC.	13 pa... 13 pages, 11 figures, 6 tables	Code Link
ResFlow: Fine-tuning Residual Optical Flow for Event-based High Temporal Resolution Motion Estimation	2024-12-12	Show Event cameras hold significant promise for high-temporal-resolution (HTR) motion estimation. However, estimating event-based HTR optical flow faces two key challenges: the absence of HTR ground-truth data and the intrinsic sparsity of event data. Most existing approaches rely on the flow accumulation paradigms to indirectly supervise intermediate flows, often resulting in accumulation errors and optimization difficulties. To address these challenges, we propose a residual-based paradigm for estimating HTR optical flow with event data. Our approach separates HTR flow estimation into two stages: global linear motion estimation and HTR residual flow refinement. The residual paradigm effectively mitigates the impacts of event sparsity on optimization and is compatible with any LTR algorithm. Next, to address the challenge posed by the absence of HTR ground truth, we incorporate novel learning strategies. Specifically, we initially employ a shared refiner to estimate the residual flows, enabling both LTR supervision and HTR inference. Subsequently, we introduce regional noise to simulate the residual patterns of intermediate flows, facilitating the adaptation from LTR supervision to HTR inference. Additionally, we show that the noise-based strategy supports in-domain self-supervised training. Comprehensive experimental results demonstrate that our approach achieves state-of-the-art accuracy in both LTR and HTR metrics, highlighting its effectiveness and superiority.	10 pages, 8 figures	None
Continuous Gaussian Process Pre-Optimization for Asynchronous Event-Inertial Odometry	2024-12-12	Show Event cameras, as bio-inspired sensors, are asynchronously triggered with high-temporal resolution compared to intensity cameras. Recent work has focused on fusing the event measurements with inertial measurements to enable ego-motion estimation in high-speed and HDR environments. However, existing methods predominantly rely on IMU preintegration designed mainly for synchronous sensors and discrete-time frameworks. In this paper, we propose a continuous-time preintegration method based on the Temporal Gaussian Process (TGP) called GPO. Concretely, we model the preintegration as a time-indexed motion trajectory and leverage an efficient two-step optimization to initialize the precision preintegration pseudo-measurements. Our method realizes a linear and constant time cost for initialization and query, respectively. To further validate the proposal, we leverage the GPO to design an asynchronous event-inertial odometry and compare with other asynchronous fusion schemes within the same odometry system. Experiments conducted on both public and own-collected datasets demonstrate that the proposed GPO offers significant advantages in terms of precision and efficiency, outperforming existing approaches in handling asynchronous sensor fusion.	8pages	None
Unified Vertex Motion Estimation for Integrated Video Stabilization and Stitching in Tractor-Trailer Wheeled Robots	2024-12-10	Show Tractor-trailer wheeled robots need to perform comprehensive perception tasks to enhance their operations in areas such as logistics parks and long-haul transportation. The perception of these robots face three major challenges: the relative pose change between the tractor and trailer, the asynchronous vibrations between the tractor and trailer, and the significant camera parallax caused by the large size. In this paper, we propose a novel Unified Vertex Motion Video Stabilization and Stitching framework designed for unknown environments. To establish the relationship between stabilization and stitching, the proposed Unified Vertex Motion framework comprises the Stitching Motion Field, which addresses relative positional change, and the Stabilization Motion Field, which tackles asynchronous vibrations. Then, recognizing the heterogeneity of optimization functions required for stabilization and stitching, a weighted cost function approach is proposed to address the problem of camera parallax. Furthermore, this framework has been successfully implemented in real tractor-trailer wheeled robots. The proposed Unified Vertex Motion Video Stabilization and Stitching method has been thoroughly tested in various challenging scenarios, demonstrating its accuracy and practicality in real-world robot tasks.		None
MotionStone: Decoupled Motion Intensity Modulation with Diffusion Transformer for Image-to-Video Generation	2024-12-08	Show The image-to-video (I2V) generation is conditioned on the static image, which has been enhanced recently by the motion intensity as an additional control signal. These motion-aware models are appealing to generate diverse motion patterns, yet there lacks a reliable motion estimator for training such models on large-scale video set in the wild. Traditional metrics, e.g., SSIM or optical flow, are hard to generalize to arbitrary videos, while, it is very tough for human annotators to label the abstract motion intensity neither. Furthermore, the motion intensity shall reveal both local object motion and global camera movement, which has not been studied before. This paper addresses the challenge with a new motion estimator, capable of measuring the decoupled motion intensities of objects and cameras in video. We leverage the contrastive learning on randomly paired videos and distinguish the video with greater motion intensity. Such a paradigm is friendly for annotation and easy to scale up to achieve stable performance on motion estimation. We then present a new I2V model, named MotionStone, developed with the decoupled motion estimator. Experimental results demonstrate the stability of the proposed motion estimator and the state-of-the-art performance of MotionStone on I2V generation. These advantages warrant the decoupled motion estimator to serve as a general plug-in enhancer for both data processing and video generation training.		None
Deformation-Aware Segmentation Network Robust to Motion Artifacts for Brain Tissue Segmentation using Disentanglement Learning	2024-12-05	Show Motion artifacts caused by prolonged acquisition time are a significant challenge in Magnetic Resonance Imaging (MRI), hindering accurate tissue segmentation. These artifacts appear as blurred images that mimic tissue-like appearances, making segmentation difficult. This study proposes a novel deep learning framework that demonstrates superior performance in both motion correction and robust brain tissue segmentation in the presence of artifacts. The core concept lies in a complementary process: a disentanglement learning network progressively removes artifacts, leading to cleaner images and consequently, more accurate segmentation by a jointly trained motion estimation and segmentation network. This network generates three outputs: a motioncorrected image, a motion deformation map that identifies artifact-affected regions, and a brain tissue segmentation mask. This deformation serves as a guidance mechanism for the disentanglement process, aiding the model in recovering lost information or removing artificial structures introduced by the artifacts. Extensive in-vivo experiments on pediatric motion data demonstrate that our proposed framework outperforms state-of-the-art methods in segmenting motion-corrupted MRI scans.	Medic... Medical Image Computing and Computer Assisted Intervention, MICCAI 2024	None
EgoCast: Forecasting Egocentric Human Pose in the Wild	2024-12-03	Show Accurately estimating and forecasting human body pose is important for enhancing the user's sense of immersion in Augmented Reality. Addressing this need, our paper introduces EgoCast, a bimodal method for 3D human pose forecasting using egocentric videos and proprioceptive data. We study the task of human pose forecasting in a realistic setting, extending the boundaries of temporal forecasting in dynamic scenes and building on the current framework for current pose estimation in the wild. We introduce a current-frame estimation module that generates pseudo-groundtruth poses for inference, eliminating the need for past groundtruth poses typically required by current methods during forecasting. Our experimental results on the recent Ego-Exo4D and Aria Digital Twin datasets validate EgoCast for real-life motion estimation. On the Ego-Exo4D Body Pose 2024 Challenge, our method significantly outperforms the state-of-the-art approaches, laying the groundwork for future research in human pose estimation and forecasting in unscripted activities with egocentric inputs.		None
BYE: Build Your Encoder with One Sequence of Exploration Data for Long-Term Dynamic Scene Understanding	2024-12-03	Show Dynamic scene understanding remains a persistent challenge in robotic applications. Early dynamic mapping methods focused on mitigating the negative influence of short-term dynamic objects on camera motion estimation by masking or tracking specific categories, which often fall short in adapting to long-term scene changes. Recent efforts address object association in long-term dynamic environments using neural networks trained on synthetic datasets, but they still rely on predefined object shapes and categories. Other methods incorporate visual, geometric, or semantic heuristics for the association but often lack robustness. In this work, we introduce BYE, a class-agnostic, per-scene point cloud encoder that removes the need for predefined categories, shape priors, or extensive association datasets. Trained on only a single sequence of exploration data, BYE can efficiently perform object association in dynamically changing scenes. We further propose an ensembling scheme combining the semantic strengths of Vision Language Models (VLMs) with the scene-specific expertise of BYE, achieving a 7% improvement and a 95% success rate in object association tasks. Code and dataset are available at https://byencoder.github.io.		None
Continuous-Time Human Motion Field from Events	2024-12-02	Show This paper addresses the challenges of estimating a continuous-time human motion field from a stream of events. Existing Human Mesh Recovery (HMR) methods rely predominantly on frame-based approaches, which are prone to aliasing and inaccuracies due to limited temporal resolution and motion blur. In this work, we predict a continuous-time human motion field directly from events by leveraging a recurrent feed-forward neural network to predict human motion in the latent space of possible human motions. Prior state-of-the-art event-based methods rely on computationally intensive optimization across a fixed number of poses at high frame rates, which becomes prohibitively expensive as we increase the temporal resolution. In comparison, we present the first work that replaces traditional discrete-time predictions with a continuous human motion field represented as a time-implicit function, enabling parallel pose queries at arbitrary temporal resolutions. Despite the promises of event cameras, few benchmarks have tested the limit of high-speed human motion estimation. We introduce Beam-splitter Event Agile Human Motion Dataset-a hardware-synchronized high-speed human dataset to fill this gap. On this new data, our method improves joint errors by 23.8% compared to previous event human methods while reducing the computational time by 69%.		None
Hybrid Local-Global Context Learning for Neural Video Compression	2024-11-30	Show In neural video codecs, current state-of-the-art methods typically adopt multi-scale motion compensation to handle diverse motions. These methods estimate and compress either optical flow or deformable offsets to reduce inter-frame redundancy. However, flow-based methods often suffer from inaccurate motion estimation in complicated scenes. Deformable convolution-based methods are more robust but have a higher bit cost for motion coding. In this paper, we propose a hybrid context generation module, which combines the advantages of the above methods in an optimal way and achieves accurate compensation at a low bit cost. Specifically, considering the characteristics of features at different scales, we adopt flow-guided deformable compensation at largest-scale to produce accurate alignment in detailed regions. For smaller-scale features, we perform flow-based warping to save the bit cost for motion coding. Furthermore, we design a local-global context enhancement module to fully explore the local-global information of previous reconstructed signals. Experimental results demonstrate that our proposed Hybrid Local-Global Context learning (HLGC) method can significantly enhance the state-of-the-art methods on standard test datasets.	Accepted to DCC 2024	None
Event-based Tracking of Any Point with Motion-Robust Correlation Features	2024-11-28	Show Tracking any point (TAP) recently shifted the motion estimation paradigm from focusing on individual salient points with local templates to tracking arbitrary points with global image contexts. However, while research has mostly focused on driving the accuracy of models in nominal settings, addressing scenarios with difficult lighting conditions and high-speed motions remains out of reach due to the limitations of the sensor. This work addresses this challenge with the first event camera-based TAP method. It leverages the high temporal resolution and high dynamic range of event cameras for robust high-speed tracking, and the global contexts in TAP methods to handle asynchronous and sparse event measurements. We further extend the TAP framework to handle event feature variations induced by motion - thereby addressing an open challenge in purely event-based tracking - with a novel feature alignment loss which ensures the learning of motion-robust features. Our method is trained with data from a new data generation pipeline and systematically ablated across all design decisions. Our method shows strong cross-dataset generalization and performs 135% better on the average Jaccard metric than the baselines. Moreover, on an established feature tracking benchmark, it achieves a 19% improvement over the previous best event-only method and even surpasses the previous best events-and-frames method by 3.7%.	14 pa... 14 pages, 12 figures, 7 tables	None
Deep End-to-end Adaptive k-Space Sampling, Reconstruction, and Registration for Dynamic MRI	2024-11-27	Show Dynamic MRI enables a range of clinical applications, including cardiac function assessment, organ motion tracking, and radiotherapy guidance. However, fully sampling the dynamic k-space data is often infeasible due to time constraints and physiological motion such as respiratory and cardiac motion. This necessitates undersampling, which degrades the quality of reconstructed images. Poor image quality not only hinders visualization but also impairs the estimation of deformation fields, crucial for registering dynamic (moving) images to a static reference image. This registration enables tasks such as motion correction, treatment planning, and quantitative analysis in applications like cardiac imaging and MR-guided radiotherapy. To overcome the challenges posed by undersampling and motion, we introduce an end-to-end deep learning (DL) framework that integrates adaptive dynamic k-space sampling, reconstruction, and registration. Our approach begins with a DL-based adaptive sampling strategy, optimizing dynamic k-space acquisition to capture the most relevant data for each specific case. This is followed by a DL-based reconstruction module that produces images optimized for accurate deformation field estimation from the undersampled moving data. Finally, a registration module estimates the deformation fields aligning the reconstructed dynamic images with a static reference. The proposed framework is independent of specific reconstruction and registration modules allowing for plug-and-play integration of these components. The entire framework is jointly trained using a combination of supervised and unsupervised loss functions, enabling end-to-end optimization for improved performance across all components. Through controlled experiments and ablation studies, we validate each component, demonstrating that each choice contributes to robust motion estimation from undersampled dynamic data.	39 pa... 39 pages, 19 figures, 4 tables	None
GMFlow: Global Motion-Guided Recurrent Flow for 6D Object Pose Estimation	2024-11-26	Show 6D object pose estimation is crucial for robotic perception and precise manipulation. Occlusion and incomplete object visibility are common challenges in this task, but existing pose refinement methods often struggle to handle these issues effectively. To tackle this problem, we propose a global motion-guided recurrent flow estimation method called GMFlow for pose estimation. GMFlow overcomes local ambiguities caused by occlusion or missing parts by seeking global explanations. We leverage the object's structural information to extend the motion of visible parts of the rigid body to its invisible regions. Specifically, we capture global contextual information through a linear attention mechanism and guide local motion information to generate global motion estimates. Furthermore, we introduce object shape constraints in the flow iteration process, making flow estimation suitable for pose estimation scenarios. Experiments on the LM-O and YCB-V datasets demonstrate that our method outperforms existing techniques in accuracy while maintaining competitive computational efficiency.		None
Motion Free B-frame Coding for Neural Video Compression	2024-11-26	Show Typical deep neural video compression networks usually follow the hybrid approach of classical video coding that contains two separate modules: motion coding and residual coding. In addition, a symmetric auto-encoder is often used as a normal architecture for both motion and residual coding. In this paper, we propose a novel approach that handles the drawbacks of the two typical above-mentioned architectures, we call it kernel-based motion-free video coding. The advantages of the motion-free approach are twofold: it improves the coding efficiency of the network and significantly reduces computational complexity thanks to eliminating motion estimation, motion compensation, and motion coding which are the most time-consuming engines. In addition, the kernel-based auto-encoder alleviates blur artifacts that usually occur with the conventional symmetric autoencoder. Consequently, it improves the visual quality of the reconstructed frames. Experimental results show the proposed framework outperforms the SOTA deep neural video compression networks on the HEVC-class B dataset and is competitive on the UVG and MCL-JCV datasets. In addition, it generates high-quality reconstructed frames in comparison with conventional motion coding-based symmetric auto-encoder meanwhile its model size is much smaller than that of the motion-based networks around three to four times.	Deep ... Deep Neural Video Compression	None
No Identity, no problem: Motion through detection for people tracking	2024-11-25	Show Tracking-by-detection has become the de facto standard approach to people tracking. To increase robustness, some approaches incorporate re-identification using appearance models and regressing motion offset, which requires costly identity annotations. In this paper, we propose exploiting motion clues while providing supervision only for the detections, which is much easier to do. Our algorithm predicts detection heatmaps at two different times, along with a 2D motion estimate between the two images. It then warps one heatmap using the motion estimate and enforces consistency with the other one. This provides the required supervisory signal on the motion without the need for any motion annotations. In this manner, we couple the information obtained from different images during training and increase accuracy, especially in crowded scenes and when using low frame-rate sequences. We show that our approach delivers state-of-the-art results for single- and multi-view multi-target tracking on the MOT17 and WILDTRACK datasets.	Accep... Accepted in TMLR November 2024	None
Efficient and Robust Registration on the 3D Special Euclidean Group	2024-11-22	Show We present an accurate, robust and fast method for registration of 3D scans. Our motion estimation optimizes a robust cost function on the intrinsic representation of rigid motions, i.e., the Special Euclidean group $\mathbb{SE}(3)$. We exploit the geometric properties of Lie groups as well as the robustness afforded by an iteratively reweighted least squares optimization. We also generalize our approach to a joint multiview method that simultaneously solves for the registration of a set of scans. We demonstrate the efficacy of our approach by thorough experimental validation. Our approach significantly outperforms the state-of-the-art robust 3D registration method based on a line process in terms of both speed and accuracy. We also show that this line process method is a special case of our principled geometric solution. Finally, we also present scenarios where global registration based on feature correspondences fails but multiview ICP based on our robust motion estimation is successful.	18 pa... 18 pages, 7 figures, 7 tables	None
U-Motion: Learned Point Cloud Video Compression with U-Structured Motion Estimation	2024-11-21	Show Point cloud video (PCV) is a versatile 3D representation of dynamic scenes with many emerging applications. This paper introduces U-Motion, a learning-based compression scheme for both PCV geometry and attributes. We propose a U-Structured multiscale inter-frame prediction framework, U-Inter, which performs layer-wise explicit motion estimation and compensation (ME/MC) at different scales with varying levels of detail. It integrates both higher and lower-scale motion features, in addition to the information of current and previous frames, to enable accurate motion estimation at the current scale. In addition, we design a cascaded spatial predictive coding module to capture the inter-scale spatial redundancy remaining after U-Inter prediction. We further propose an effective context detach and restore scheme to reduce spatial-temporal redundancy in the motion and latent bit-streams and improve compression performance. We conduct experiments following the MPEG Common Test Condition and demonstrate that U-Motion can achieve significant gains over MPEG G-PCC-GesTM v3.0 and recently published learning-based methods for both geometry and attribute compression.		None
AsynEIO: Asynchronous Monocular Event-Inertial Odometry Using Gaussian Process Regression	2024-11-19	Show Event cameras, when combined with inertial sensors, show significant potential for motion estimation in challenging scenarios, such as high-speed maneuvers and low-light environments. There are many methods for producing such estimations, but most boil down to a synchronous discrete-time fusion problem. However, the asynchronous nature of event cameras and their unique fusion mechanism with inertial sensors remain underexplored. In this paper, we introduce a monocular event-inertial odometry method called AsynEIO, designed to fuse asynchronous event and inertial data within a unified Gaussian Process (GP) regression framework. Our approach incorporates an event-driven frontend that tracks feature trajectories directly from raw event streams at a high temporal resolution. These tracked feature trajectories, along with various inertial factors, are integrated into the same GP regression framework to enable asynchronous fusion. With deriving analytical residual Jacobians and noise models, our method constructs a factor graph that is iteratively optimized and pruned using a sliding-window optimizer. Comparative assessments highlight the performance of different inertial fusion strategies, suggesting optimal choices for varying conditions. Experimental results on both public datasets and our own event-inertial sequences indicate that AsynEIO outperforms existing methods, especially in high-speed and low-illumination scenarios.	Submi... Submitted to IEEE (2024-11-4)	None
LiDAR-BEVMTN: Real-Time LiDAR Bird's-Eye View Multi-Task Perception Network for Autonomous Driving	2024-11-18	Show LiDAR is crucial for robust 3D scene perception in autonomous driving. LiDAR perception has the largest body of literature after camera perception. However, multi-task learning across tasks like detection, segmentation, and motion estimation using LiDAR remains relatively unexplored, especially on automotive-grade embedded platforms. We present a real-time multi-task convolutional neural network for LiDAR-based object detection, semantics, and motion segmentation. The unified architecture comprises a shared encoder and task-specific decoders, enabling joint representation learning. We propose a novel Semantic Weighting and Guidance (SWAG) module to transfer semantic features for improved object detection selectively. Our heterogeneous training scheme combines diverse datasets and exploits complementary cues between tasks. The work provides the first embedded implementation unifying these key perception tasks from LiDAR point clouds achieving 3ms latency on the embedded NVIDIA Xavier platform. We achieve state-of-the-art results for two tasks, semantic and motion segmentation, and close to state-of-the-art performance for 3D object detection. By maximizing hardware efficiency and leveraging multi-task synergies, our method delivers an accurate and efficient solution tailored for real-world automated driving deployment. Qualitative results can be seen at https://youtu.be/H-hWRzv2lIY.	Accep... Accepted for publication at IEEE Transactions on Intelligent Transportation Systems	None
RINO: Accurate, Robust Radar-Inertial Odometry with Non-Iterative Estimation	2024-11-16	Show Precise localization and mapping are critical for achieving autonomous navigation in self-driving vehicles. However, ego-motion estimation still faces significant challenges, particularly when GNSS failures occur or under extreme weather conditions (e.g., fog, rain, and snow). In recent years, scanning radar has emerged as an effective solution due to its strong penetration capabilities. Nevertheless, scanning radar data inherently contains high levels of noise, necessitating hundreds to thousands of iterations of optimization to estimate a reliable transformation from the noisy data. Such iterative solving is time-consuming, unstable, and prone to failure. To address these challenges, we propose an accurate and robust Radar-Inertial Odometry system, RINO, which employs a non-iterative solving approach. Our method decouples rotation and translation estimation and applies an adaptive voting scheme for 2D rotation estimation, enhancing efficiency while ensuring consistent solving time. Additionally, the approach implements a loosely coupled system between the scanning radar and an inertial measurement unit (IMU), leveraging Error-State Kalman Filtering (ESKF). Notably, we successfully estimated the uncertainty of the pose estimation from the scanning radar, incorporating this into the filter's Maximum A Posteriori estimation, a consideration that has been previously overlooked. Validation on publicly available datasets demonstrates that RINO outperforms state-of-the-art methods and baselines in both accuracy and robustness. Our code is available at https://github.com/yangsc4063/rino.		Code Link
BEV-ODOM: Reducing Scale Drift in Monocular Visual Odometry with BEV Representation	2024-11-15	Show Monocular visual odometry (MVO) is vital in autonomous navigation and robotics, providing a cost-effective and flexible motion tracking solution, but the inherent scale ambiguity in monocular setups often leads to cumulative errors over time. In this paper, we present BEV-ODOM, a novel MVO framework leveraging the Bird's Eye View (BEV) Representation to address scale drift. Unlike existing approaches, BEV-ODOM integrates a depth-based perspective-view (PV) to BEV encoder, a correlation feature extraction neck, and a CNN-MLP-based decoder, enabling it to estimate motion across three degrees of freedom without the need for depth supervision or complex optimization techniques. Our framework reduces scale drift in long-term sequences and achieves accurate motion estimation across various datasets, including NCLT, Oxford, and KITTI. The results indicate that BEV-ODOM outperforms current MVO methods, demonstrating reduced scale drift and higher accuracy.		None
iKalibr: Unified Targetless Spatiotemporal Calibration for Resilient Integrated Inertial Systems	2024-11-14	Show The integrated inertial system, typically integrating an IMU and an exteroceptive sensor such as radar, LiDAR, and camera, has been widely accepted and applied in modern robotic applications for ego-motion estimation, motion control, or autonomous exploration. To improve system accuracy, robustness, and further usability, both multiple and various sensors are generally resiliently integrated, which benefits the system performance regarding failure tolerance, perception capability, and environment compatibility. For such systems, accurate and consistent spatiotemporal calibration is required to maintain a unique spatiotemporal framework for multi-sensor fusion. Considering most existing calibration methods (i) are generally oriented to specific integrated inertial systems, (ii) often only focus on spatial determination, (iii) usually require artificial targets, lacking convenience and usability, we propose iKalibr: a unified targetless spatiotemporal calibration framework for resilient integrated inertial systems, which overcomes the above issues, and enables both accurate and consistent calibration. Altogether four commonly employed sensors are supported in iKalibr currently, namely IMU, radar, LiDAR, and camera. The proposed method starts with a rigorous and efficient dynamic initialization, where all parameters in the estimator would be accurately recovered. Subsequently, several continuous-time batch optimizations are conducted to refine the initialized parameters toward better states. Sufficient real-world experiments were conducted to verify the feasibility and evaluate the calibration performance of iKalibr. The results demonstrate that iKalibr can achieve accurate resilient spatiotemporal calibration. We open-source our implementations at (https://github.com/Unsigned-Long/iKalibr) to benefit the research community.		Code Link
Inter-Frame Coding for Dynamic Meshes via Coarse-to-Fine Anchor Mesh Generation	2024-11-06	Show In the current Video-based Dynamic Mesh Coding (V-DMC) standard, inter-frame coding is restricted to mesh frames with constant topology. Consequently, temporal redundancy is not fully leveraged, resulting in suboptimal compression efficacy. To address this limitation, this paper introduces a novel coarse-to-fine scheme to generate anchor meshes for frames with time-varying topology. Initially, we generate a coarse anchor mesh using an octree-based nearest neighbor search. Motion estimation compensates for regions with significant motion changes during this process. However, the quality of the coarse mesh is low due to its suboptimal vertices. To enhance details, the fine anchor mesh is further optimized using the Quadric Error Metrics (QEM) algorithm to calculate more precise anchor points. The inter-frame anchor mesh generated herein retains the connectivity of the reference base mesh, while concurrently preserving superior quality. Experimental results show that our method achieves 7.2% ~ 10.3% BD-rate gain compared to the existing V-DMC test model version 7.		None
Automatic Target-Less Camera-LiDAR Calibration From Motion and Deep Point Correspondences	2024-11-04	Show Sensor setups of robotic platforms commonly include both camera and LiDAR as they provide complementary information. However, fusing these two modalities typically requires a highly accurate calibration between them. In this paper, we propose MDPCalib which is a novel method for camera-LiDAR calibration that requires neither human supervision nor any specific target objects. Instead, we utilize sensor motion estimates from visual and LiDAR odometry as well as deep learning-based 2D-pixel-to-3D-point correspondences that are obtained without in-domain retraining. We represent camera-LiDAR calibration as an optimization problem and minimize the costs induced by constraints from sensor motion and point correspondences. In extensive experiments, we demonstrate that our approach yields highly accurate extrinsic calibration parameters and is robust to random initialization. Additionally, our approach generalizes to a wide range of sensor setups, which we demonstrate by employing it on various robotic platforms including a self-driving perception car, a quadruped robot, and a UAV. To make our calibration method publicly accessible, we release the code on our project website at http://calibration.cs.uni-freiburg.de.		None
SISMIK for brain MRI: Deep-learning-based motion estimation and model-based motion correction in k-space	2024-11-03	Show MRI, a widespread non-invasive medical imaging modality, is highly sensitive to patient motion. Despite many attempts over the years, motion correction remains a difficult problem and there is no general method applicable to all situations. We propose a retrospective method for motion estimation and correction to tackle the problem of in-plane rigid-body motion, apt for classical 2D Spin-Echo scans of the brain, which are regularly used in clinical practice. Due to the sequential acquisition of k-space, motion artifacts are well localized. The method leverages the power of deep neural networks to estimate motion parameters in k-space and uses a model-based approach to restore degraded images to avoid ''hallucinations''. Notable advantages are its ability to estimate motion occurring in high spatial frequencies without the need of a motion-free reference. The proposed method operates on the whole k-space dynamic range and is moderately affected by the lower SNR of higher harmonics. As a proof of concept, we provide models trained using supervised learning on 600k motion simulations based on motion-free scans of 43 different subjects. Generalization performance was tested with simulations as well as in-vivo. Qualitative and quantitative evaluations are presented for motion parameter estimations and image reconstruction. Experimental results show that our approach is able to obtain good generalization performance on simulated data and in-vivo acquisitions. We provide a Python implementation at https://gitlab.unige.ch/Oscar.Dabrowski/sismik_mri/.		None
GPTR: Gaussian Process Trajectory Representation for Continuous-Time Motion Estimation	2024-11-02	Show Continuous-time trajectory representation has gained significant popularity in recent years, as it offers an elegant formulation that allows the fusion of a larger number of sensors and sensing modalities, overcoming limitations of traditional discrete-time frameworks. To bolster the adoption of the continuous-time paradigm, we propose a so-called Gaussian Process Trajectory Representation (GPTR) framework for continuous-time motion estimation (CTME) tasks. Our approach stands out by employing a third-order random jerk model, featuring closed-form expressions for both rotational and translational state derivatives. This model provides smooth, continuous trajectory representations that are crucial for precise estimation of complex motion. To support the wider robotics and computer vision communities, we have made the source code for GPTR available as a light-weight header-only library. This format was chosen for its ease of integration, allowing developers to incorporate GPTR into existing systems without needing extensive code modifications. Moreover, we also provide a set of optimization examples with LiDAR, camera, IMU, UWB factors, and closed-form analytical Jacobians under the proposed GP framework. Our experiments demonstrate the efficacy and efficiency of GP-based trajectory representation in various motion estimation tasks, and the examples can serve as the prototype to help researchers quickly develop future applications such as batch optimization, calibration, sensor fusion, trajectory planning, etc., with continuous-time trajectory representation. Our project is accessible at https://github.com/brytsknguyen/gptr .	The s... The source code has been released. All feedbacks are welcome	Code Link
A survey on deep learning in medical image registration: new technologies, uncertainty, evaluation metrics, and beyond	2024-11-01	Show Deep learning technologies have dramatically reshaped the field of medical image registration over the past decade. The initial developments, such as regression-based and U-Net-based networks, established the foundation for deep learning in image registration. Subsequent progress has been made in various aspects of deep learning-based registration, including similarity measures, deformation regularizations, network architectures, and uncertainty estimation. These advancements have not only enriched the field of image registration but have also facilitated its application in a wide range of tasks, including atlas construction, multi-atlas segmentation, motion estimation, and 2D-3D registration. In this paper, we present a comprehensive overview of the most recent advancements in deep learning-based image registration. We begin with a concise introduction to the core concepts of deep learning-based image registration. Then, we delve into innovative network architectures, loss functions specific to registration, and methods for estimating registration uncertainty. Additionally, this paper explores appropriate evaluation metrics for assessing the performance of deep learning models in registration tasks. Finally, we highlight the practical applications of these novel techniques in medical imaging and discuss the future prospects of deep learning-based image registration.	Accep... Accepted to Medical Image Analysis ((c) MedIA). A list of open-sourced code from the papers reviewed has been organized and is available at https://bit.ly/3QgFJ9z	None
Fast-OMRA: Fast Online Motion Resolution Adaptation for Neural B-Frame Coding	2024-10-29	Show Most learned B-frame codecs with hierarchical temporal prediction suffer from the domain shift issue caused by the discrepancy in the Group-of-Pictures (GOP) size used for training and test. As such, the motion estimation network may fail to predict large motion properly. One effective strategy to mitigate this domain shift issue is to downsample video frames for motion estimation. However, finding the optimal downsampling factor involves a time-consuming rate-distortion optimization process. This work introduces lightweight classifiers to determine the downsampling factor. To strike a good rate-distortion-complexity trade-off, our classifiers observe simple state signals, including only the coding and reference frames, to predict the best downsampling factor. We present two variants that adopt binary and multi-class classifiers, respectively. The binary classifier adopts the Focal Loss for training, classifying between motion estimation at high and low resolutions. Our multi-class classifier is trained with novel soft labels incorporating the knowledge of the rate-distortion costs of different downsampling factors. Both variants operate as add-on modules without the need to re-train the B-frame codec. Experimental results confirm that they achieve comparable coding performance to the brute-force search methods while greatly reducing computational complexity.		None
A New Wave in Robotics: Survey on Recent mmWave Radar Applications in Robotics	2024-10-28	Show We survey the current state of millimeterwave (mmWave) radar applications in robotics with a focus on unique capabilities, and discuss future opportunities based on the state of the art. Frequency Modulated Continuous Wave (FMCW) mmWave radars operating in the 76--81GHz range are an appealing alternative to lidars, cameras and other sensors operating in the near visual spectrum. Radar has been made more widely available in new packaging classes, more convenient for robotics and its longer wavelengths have the ability to bypass visual clutter such as fog, dust, and smoke. We begin by covering radar principles as they relate to robotics. We then review the relevant new research across a broad spectrum of robotics applications beginning with motion estimation, localization, and mapping. We then cover object detection and classification, and then close with an analysis of current datasets and calibration techniques that provide entry points into radar research.	20 Pa... 20 Pages, 7 Figures, 2 Tables, TRO Submission pending	None
FastPCI: Motion-Structure Guided Fast Point Cloud Frame Interpolation	2024-10-25	Show Point cloud frame interpolation is a challenging task that involves accurate scene flow estimation across frames and maintaining the geometry structure. Prevailing techniques often rely on pre-trained motion estimators or intensive testing-time optimization, resulting in compromised interpolation accuracy or prolonged inference. This work presents FastPCI that introduces Pyramid Convolution-Transformer architecture for point cloud frame interpolation. Our hybrid Convolution-Transformer improves the local and long-range feature learning, while the pyramid network offers multilevel features and reduces the computation. In addition, FastPCI proposes a unique Dual-Direction Motion-Structure block for more accurate scene flow estimation. Our design is motivated by two facts: (1) accurate scene flow preserves 3D structure, and (2) point cloud at the previous timestep should be reconstructable using reverse motion from future timestep. Extensive experiments show that FastPCI significantly outperforms the state-of-the-art PointINet and NeuralPCI with notable gains (e.g. 26.6% and 18.3% reduction in Chamfer Distance in KITTI), while being more than 10x and 600x faster, respectively. Code is available at https://github.com/genuszty/FastPCI	To ap... To appear in ECCV 2024	Code Link
Highly efficient non-rigid registration in k-space with application to cardiac Magnetic Resonance Imaging	2024-10-24	Show In Magnetic Resonance Imaging (MRI), high temporal-resolved motion can be useful for image acquisition and reconstruction, MR-guided radiotherapy, dynamic contrast-enhancement, flow and perfusion imaging, and functional assessment of motion patterns in cardiovascular, abdominal, peristaltic, fetal, or musculoskeletal imaging. Conventionally, these motion estimates are derived through image-based registration, a particularly challenging task for complex motion patterns and high dynamic resolution. The accelerated scans in such applications result in imaging artifacts that compromise the motion estimation. In this work, we propose a novel self-supervised deep learning-based framework, dubbed the Local-All Pass Attention Network (LAPANet), for non-rigid motion estimation directly from the acquired accelerated Fourier space, i.e. k-space. The proposed approach models non-rigid motion as the cumulative sum of local translational displacements, following the Local All-Pass (LAP) registration technique. LAPANet was evaluated on cardiac motion estimation across various sampling trajectories and acceleration rates. Our results demonstrate superior accuracy compared to prior conventional and deep learning-based registration methods, accommodating as few as 2 lines/frame in a Cartesian trajectory and 3 spokes/frame in a non-Cartesian trajectory. The achieved high temporal resolution (less than 5 ms) for non-rigid motion opens new avenues for motion detection, tracking and correction in dynamic and real-time MRI applications.		None
Efficient Neural Implicit Representation for 3D Human Reconstruction	2024-10-23	Show High-fidelity digital human representations are increasingly in demand in the digital world, particularly for interactive telepresence, AR/VR, 3D graphics, and the rapidly evolving metaverse. Even though they work well in small spaces, conventional methods for reconstructing 3D human motion frequently require the use of expensive hardware and have high processing costs. This study presents HumanAvatar, an innovative approach that efficiently reconstructs precise human avatars from monocular video sources. At the core of our methodology, we integrate the pre-trained HuMoR, a model celebrated for its proficiency in human motion estimation. This is adeptly fused with the cutting-edge neural radiance field technology, Instant-NGP, and the state-of-the-art articulated model, Fast-SNARF, to enhance the reconstruction fidelity and speed. By combining these two technologies, a system is created that can render quickly and effectively while also providing estimation of human pose parameters that are unmatched in accuracy. We have enhanced our system with an advanced posture-sensitive space reduction technique, which optimally balances rendering quality with computational efficiency. In our detailed experimental analysis using both artificial and real-world monocular videos, we establish the advanced performance of our approach. HumanAvatar consistently equals or surpasses contemporary leading-edge reconstruction techniques in quality. Furthermore, it achieves these complex reconstructions in minutes, a fraction of the time typically required by existing methods. Our models achieve a training speed that is 110X faster than that of State-of-The-Art (SoTA) NeRF-based models. Our technique performs noticeably better than SoTA dynamic human NeRF methods if given an identical runtime limit. HumanAvatar can provide effective visuals after only 30 seconds of training.		None
A gradient-based approach to fast and accurate head motion compensation in cone-beam CT	2024-10-21	Show Cone-beam computed tomography (CBCT) systems, with their flexibility, present a promising avenue for direct point-of-care medical imaging, particularly in critical scenarios such as acute stroke assessment. However, the integration of CBCT into clinical workflows faces challenges, primarily linked to long scan duration resulting in patient motion during scanning and leading to image quality degradation in the reconstructed volumes. This paper introduces a novel approach to CBCT motion estimation using a gradient-based optimization algorithm, which leverages generalized derivatives of the backprojection operator for cone-beam CT geometries. Building on that, a fully differentiable target function is formulated which grades the quality of the current motion estimate in reconstruction space. We drastically accelerate motion estimation yielding a 19-fold speed-up compared to existing methods. Additionally, we investigate the architecture of networks used for quality metric regression and propose predicting voxel-wise quality maps, favoring autoencoder-like architectures over contracting ones. This modification improves gradient flow, leading to more accurate motion estimation. The presented method is evaluated through realistic experiments on head anatomy. It achieves a reduction in reprojection error from an initial average of 3mm to 0.61mm after motion compensation and consistently demonstrates superior performance compared to existing approaches. The analytic Jacobian for the backprojection operation, which is at the core of the proposed method, is made publicly available. In summary, this paper contributes to the advancement of CBCT integration into clinical workflows by proposing a robust motion estimation approach that enhances efficiency and accuracy, addressing critical challenges in time-sensitive scenarios.	\copy... \copyright 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works	None
IncEventGS: Pose-Free Gaussian Splatting from a Single Event Camera	2024-10-18	Show Implicit neural representation and explicit 3D Gaussian Splatting (3D-GS) for novel view synthesis have achieved remarkable progress with frame-based camera (e.g. RGB and RGB-D cameras) recently. Compared to frame-based camera, a novel type of bio-inspired visual sensor, i.e. event camera, has demonstrated advantages in high temporal resolution, high dynamic range, low power consumption and low latency. Due to its unique asynchronous and irregular data capturing process, limited work has been proposed to apply neural representation or 3D Gaussian splatting for an event camera. In this work, we present IncEventGS, an incremental 3D Gaussian Splatting reconstruction algorithm with a single event camera. To recover the 3D scene representation incrementally, we exploit the tracking and mapping paradigm of conventional SLAM pipelines for IncEventGS. Given the incoming event stream, the tracker firstly estimates an initial camera motion based on prior reconstructed 3D-GS scene representation. The mapper then jointly refines both the 3D scene representation and camera motion based on the previously estimated motion trajectory from the tracker. The experimental results demonstrate that IncEventGS delivers superior performance compared to prior NeRF-based methods and other related baselines, even we do not have the ground-truth camera poses. Furthermore, our method can also deliver better performance compared to state-of-the-art event visual odometry methods in terms of camera motion estimation. Code is publicly available at: https://github.com/wu-cvgl/IncEventGS.	Code ... Code Page: https://github.com/wu-cvgl/IncEventGS	Code Link
Dual-frame Fluid Motion Estimation with Test-time Optimization and Zero-divergence Loss	2024-10-15	Show 3D particle tracking velocimetry (PTV) is a key technique for analyzing turbulent flow, one of the most challenging computational problems of our century. At the core of 3D PTV is the dual-frame fluid motion estimation algorithm, which tracks particles across two consecutive frames. Recently, deep learning-based methods have achieved impressive accuracy in dual-frame fluid motion estimation; however, they heavily depend on large volumes of labeled data. In this paper, we introduce a new method that is completely self-supervised and notably outperforms its fully-supervised counterparts while requiring only 1% of the training samples (without labels) used by previous methods. Our method features a novel zero-divergence loss that is specific to the domain of turbulent flow. Inspired by the success of splat operation in high-dimensional filtering and random fields, we propose a splat-based implementation for this loss which is both efficient and effective. The self-supervised nature of our method naturally supports test-time optimization, leading to the development of a tailored Dynamic Velocimetry Enhancer (DVE) module. We demonstrate that strong cross-domain robustness is achieved through test-time optimization on unseen leave-one-out synthetic domains and real physical/biological domains. Code, data and models are available at https://github.com/Forrest-110/FluidMotionNet.	Accep... Accepted by NeurIPS 2024	Code Link
Adaptive Ankle Torque Control for Bipedal Humanoid Walking on Surfaces with Unknown Horizontal and Vertical Motion	2024-10-15	Show Achieving stable bipedal walking on surfaces with unknown motion remains a challenging control problem due to the hybrid, time-varying, partially unknown dynamics of the robot and the difficulty of accurate state and surface motion estimation. Surface motion imposes uncertainty on both system parameters and non-homogeneous disturbance in the walking robot dynamics. In this paper, we design an adaptive ankle torque controller to simultaneously address these two uncertainties and propose a step-length planner to minimize the required control torque. Typically, an adaptive controller is used for a continuous system. To apply adaptive control on a hybrid system such as a walking robot, an intermediate command profile is introduced to ensure a continuous error system. Simulations on a planar bipedal robot, along with comparisons against a baseline controller, demonstrate that the proposed approach effectively ensures stable walking and accurate tracking under unknown, time-varying disturbances.		None
Online learning in motion modeling for intra-interventional image sequences	2024-10-15	Show Image monitoring and guidance during medical examinations can aid both diagnosis and treatment. However, the sampling frequency is often too low, which creates a need to estimate the missing images. We present a probabilistic motion model for sequential medical images, with the ability to both estimate motion between acquired images and forecast the motion ahead of time. The core is a low-dimensional temporal process based on a linear Gaussian state-space model with analytically tractable solutions for forecasting, simulation, and imputation of missing samples. The results, from two experiments on publicly available cardiac datasets, show reliable motion estimates and an improved forecasting performance using patient-specific adaptation by online learning.	Medic... Medical Image Computing and Computer Assisted Intervention (MICCAI) 2024	None
Beyond GFVC: A Progressive Face Video Compression Framework with Adaptive Visual Tokens	2024-10-11	Show Recently, deep generative models have greatly advanced the progress of face video coding towards promising rate-distortion performance and diverse application functionalities. Beyond traditional hybrid video coding paradigms, Generative Face Video Compression (GFVC) relying on the strong capabilities of deep generative models and the philosophy of early Model-Based Coding (MBC) can facilitate the compact representation and realistic reconstruction of visual face signal, thus achieving ultra-low bitrate face video communication. However, these GFVC algorithms are sometimes faced with unstable reconstruction quality and limited bitrate ranges. To address these problems, this paper proposes a novel Progressive Face Video Compression framework, namely PFVC, that utilizes adaptive visual tokens to realize exceptional trade-offs between reconstruction robustness and bandwidth intelligence. In particular, the encoder of the proposed PFVC projects the high-dimensional face signal into adaptive visual tokens in a progressive manner, whilst the decoder can further reconstruct these adaptive visual tokens for motion estimation and signal synthesis with different granularity levels. Experimental results demonstrate that the proposed PFVC framework can achieve better coding flexibility and superior rate-distortion performance in comparison with the latest Versatile Video Coding (VVC) codec and the state-of-the-art GFVC algorithms. The project page can be found at https://github.com/Berlin0610/PFVC.		Code Link
Cell Tracking according to Biological Needs -- Strong Mitosis-aware Multi-Hypothesis Tracker with Aleatoric Uncertainty	2024-10-09	Show Cell tracking and segmentation assist biologists in extracting insights from large-scale microscopy time-lapse data. Driven by local accuracy metrics, current tracking approaches often suffer from a lack of long-term consistency and the ability to reconstruct lineage trees correctly. To address this issue, we introduce an uncertainty estimation technique for motion estimation frameworks and extend the multi-hypothesis tracking framework. Our uncertainty estimation lifts motion representations into probabilistic spatial densities using problem-specific test-time augmentations. Moreover, we introduce a novel mitosis-aware assignment problem formulation that allows multi-hypothesis trackers to model cell splits and to resolve false associations and mitosis detections based on long-term conflicts. In our framework, explicit biological knowledge is modeled in assignment costs. We evaluate our approach on nine competitive datasets and demonstrate that we outperform the current state-of-the-art on biologically inspired metrics substantially, achieving improvements by a factor of approximately 6 and uncover new insights into the behavior of motion estimation uncertainty.	13 pa... 13 pages, 4 figures, 4 tables	None
Initialization of Monocular Visual Navigation for Autonomous Agents Using Modified Structure from Small Motion	2024-10-07	Show We propose a standalone monocular visual Simultaneous Localization and Mapping (vSLAM) initialization pipeline for autonomous space robots. Our method, a state-of-the-art factor graph optimization pipeline, extends Structure from Small Motion (SfSM) to robustly initialize a monocular agent in spacecraft inspection trajectories, addressing visual estimation challenges such as weak-perspective projection and center-pointing motion, which exacerbates the bas-relief ambiguity, dominant planar geometry, which causes motion estimation degeneracies in classical Structure from Motion, and dynamic illumination conditions, which reduce the survivability of visual information. We validate our approach on realistic, simulated satellite inspection image sequences with a tumbling spacecraft and demonstrate the method's effectiveness over existing monocular initialization procedures.	6 pag... 6 pages, 1 page for references, 6 figures, 1 table, IEEEtran format. This work has been submitted to ACC for possible publication as an invited session paper	None
High-Efficiency Neural Video Compression via Hierarchical Predictive Learning	2024-10-03	Show The enhanced Deep Hierarchical Video Compression-DHVC 2.0-has been introduced. This single-model neural video codec operates across a broad range of bitrates, delivering not only superior compression performance to representative methods but also impressive complexity efficiency, enabling real-time processing with a significantly smaller memory footprint on standard GPUs. These remarkable advancements stem from the use of hierarchical predictive coding. Each video frame is uniformly transformed into multiscale representations through hierarchical variational autoencoders. For a specific scale's feature representation of a frame, its corresponding latent residual variables are generated by referencing lower-scale spatial features from the same frame and then conditionally entropy-encoded using a probabilistic model whose parameters are predicted using same-scale temporal reference from previous frames and lower-scale spatial reference of the current frame. This feature-space processing operates from the lowest to the highest scale of each frame, completely eliminating the need for the complexity-intensive motion estimation and compensation techniques that have been standard in video codecs for decades. The hierarchical approach facilitates parallel processing, accelerating both encoding and decoding, and supports transmission-friendly progressive decoding, making it particularly advantageous for networked video applications in the presence of packet loss. Source codes will be made available.		None
Correspondences of the Third Kind: Camera Pose Estimation from Object Reflection	2024-09-30	Show Computer vision has long relied on two kinds of correspondences: pixel correspondences in images and 3D correspondences on object surfaces. Is there another kind, and if there is, what can they do for us? In this paper, we introduce correspondences of the third kind we call reflection correspondences and show that they can help estimate camera pose by just looking at objects without relying on the background. Reflection correspondences are point correspondences in the reflected world, i.e., the scene reflected by the object surface. The object geometry and reflectance alters the scene geometrically and radiometrically, respectively, causing incorrect pixel correspondences. Geometry recovered from each image is also hampered by distortions, namely generalized bas-relief ambiguity, leading to erroneous 3D correspondences. We show that reflection correspondences can resolve the ambiguities arising from these distortions. We introduce a neural correspondence estimator and a RANSAC algorithm that fully leverages all three kinds of correspondences for robust and accurate joint camera pose and object shape estimation just from the object appearance. The method expands the horizon of numerous downstream tasks, including camera pose estimation for appearance modeling (e.g., NeRF) and motion estimation of reflective objects (e.g., cars on the road), to name a few, as it relieves the requirement of overlapping background.	ECCV 2024	None
DynORecon: Dynamic Object Reconstruction for Navigation	2024-09-30	Show This paper presents DynORecon, a Dynamic Object Reconstruction system that leverages the information provided by Dynamic SLAM to simultaneously generate a volumetric map of observed moving entities while estimating free space to support navigation. By capitalising on the motion estimations provided by Dynamic SLAM, DynORecon continuously refines the representation of dynamic objects to eliminate residual artefacts from past observations and incrementally reconstructs each object, seamlessly integrating new observations to capture previously unseen structures. Our system is highly efficient (~20 FPS) and produces accurate (~10 cm) reconstructions of dynamic objects using simulated and real-world outdoor datasets.	7 pag... 7 pages, 6 figures, submitted to ICRA 2025	None
Platypose: Calibrated Zero-Shot Multi-Hypothesis 3D Human Motion Estimation	2024-09-27	Show Single camera 3D pose estimation is an ill-defined problem due to inherent ambiguities from depth, occlusion or keypoint noise. Multi-hypothesis pose estimation accounts for this uncertainty by providing multiple 3D poses consistent with the 2D measurements. Current research has predominantly concentrated on generating multiple hypotheses for single frame static pose estimation or single hypothesis motion estimation. In this study we focus on the new task of multi-hypothesis motion estimation. Multi-hypothesis motion estimation is not simply multi-hypothesis pose estimation applied to multiple frames, which would ignore temporal correlation across frames. Instead, it requires distributions which are capable of generating temporally consistent samples, which is significantly more challenging than multi-hypothesis pose estimation or single-hypothesis motion estimation. To this end, we introduce Platypose, a framework that uses a diffusion model pretrained on 3D human motion sequences for zero-shot 3D pose sequence estimation. Platypose outperforms baseline methods on multiple hypotheses for motion estimation. Additionally, Platypose also achieves state-of-the-art calibration and competitive joint error when tested on static poses from Human3.6M, MPI-INF-3DHP and 3DPW. Finally, because it is zero-shot, our method generalizes flexibly to different settings such as multi-camera inference.		None
MotionTTT: 2D Test-Time-Training Motion Estimation for 3D Motion Corrected MRI	2024-09-14	Show A major challenge of the long measurement times in magnetic resonance imaging (MRI), an important medical imaging technology, is that patients may move during data acquisition. This leads to severe motion artifacts in the reconstructed images and volumes. In this paper, we propose a deep learning-based test-time-training method for accurate motion estimation. The key idea is that a neural network trained for motion-free reconstruction has a small loss if there is no motion, thus optimizing over motion parameters passed through the reconstruction network enables accurate estimation of motion. The estimated motion parameters enable to correct for the motion and to reconstruct accurate motion-corrected images. Our method uses 2D reconstruction networks to estimate rigid motion in 3D, and constitutes the first deep learning based method for 3D rigid motion estimation towards 3D-motion-corrected MRI. We show that our method can provably reconstruct motion parameters for a simple signal and neural network model. We demonstrate the effectiveness of our method for both retrospectively simulated motion and prospectively collected real motion-corrupted data.		None
Object Segmentation-Assisted Inter Prediction for Versatile Video Coding	2024-09-12	Show In modern video coding standards, block-based inter prediction is widely adopted, which brings high compression efficiency. However, in natural videos, there are usually multiple moving objects of arbitrary shapes, resulting in complex motion fields that are difficult to represent compactly. This problem has been tackled by more flexible block partitioning methods in the Versatile Video Coding (VVC) standard, but the more flexible partitions require more overhead bits to signal and still cannot be made arbitrarily shaped. To address this limitation, we propose an object segmentation-assisted inter prediction method (SAIP), where objects in the reference frames are segmented by some advanced technologies. With a proper indication, the object segmentation mask is translated from the reference frame to the current frame as the arbitrary-shaped partition of different regions without any extra signal. Using the segmentation mask, motion compensation is separately performed for different regions, achieving higher prediction accuracy. The segmentation mask is further used to code the motion vectors of different regions more efficiently. Moreover, the segmentation mask is considered in the joint rate-distortion optimization for motion estimation and partition estimation to derive the motion vector of different regions and partition more accurately. The proposed method is implemented into the VVC reference software, VTM version 12.0. Experimental results show that the proposed method achieves up to 1.98%, 1.14%, 0.79%, and on average 0.82%, 0.49%, 0.37% BD-rate reduction for common test sequences, under the Low-delay P, Low-delay B, and Random Access configurations, respectively.	20 pa... 20 pages, 13 figures, accepted by IEEE Transactions on Broadcasting (TBC)	None
LEIA: Latent View-invariant Embeddings for Implicit 3D Articulation	2024-09-10	Show Neural Radiance Fields (NeRFs) have revolutionized the reconstruction of static scenes and objects in 3D, offering unprecedented quality. However, extending NeRFs to model dynamic objects or object articulations remains a challenging problem. Previous works have tackled this issue by focusing on part-level reconstruction and motion estimation for objects, but they often rely on heuristics regarding the number of moving parts or object categories, which can limit their practical use. In this work, we introduce LEIA, a novel approach for representing dynamic 3D objects. Our method involves observing the object at distinct time steps or "states" and conditioning a hypernetwork on the current state, using this to parameterize our NeRF. This approach allows us to learn a view-invariant latent representation for each state. We further demonstrate that by interpolating between these states, we can generate novel articulation configurations in 3D space that were previously unseen. Our experimental results highlight the effectiveness of our method in articulating objects in a manner that is independent of the viewing angle and joint configuration. Notably, our approach outperforms previous methods that rely on motion information for articulation registration.	Accep... Accepted to ECCV 2024. Project Website at https://archana1998.github.io/leia/	Code Link
SiamMo: Siamese Motion-Centric 3D Object Tracking	2024-09-09	Show Current 3D single object tracking methods primarily rely on the Siamese matching-based paradigm, which struggles with textureless and incomplete LiDAR point clouds. Conversely, the motion-centric paradigm avoids appearance matching, thus overcoming these issues. However, its complex multi-stage pipeline and the limited temporal modeling capability of a single-stream architecture constrain its potential. In this paper, we introduce SiamMo, a novel and simple Siamese motion-centric tracking approach. Unlike the traditional single-stream architecture, we employ Siamese feature extraction for motion-centric tracking. This decouples feature extraction from temporal fusion, significantly enhancing tracking performance. Additionally, we design a Spatio-Temporal Feature Aggregation module to integrate Siamese features at multiple scales, capturing motion information effectively. We also introduce a Box-aware Feature Encoding module to encode object size priors into motion estimation. SiamMo is a purely motion-centric tracker that eliminates the need for additional processes like segmentation and box refinement. Without whistles and bells, SiamMo not only surpasses state-of-the-art methods across multiple benchmarks but also demonstrates exceptional robustness in challenging scenarios. SiamMo sets a new record on the KITTI tracking benchmark with 90.1% precision while maintaining a high inference speed of 108 FPS. The code will be released at https://github.com/HDU-VRLab/SiamMo.		Code Link
Future Does Matter: Boosting 3D Object Detection with Temporal Motion Estimation in Point Cloud Sequences	2024-09-06	Show Accurate and robust LiDAR 3D object detection is essential for comprehensive scene understanding in autonomous driving. Despite its importance, LiDAR detection performance is limited by inherent constraints of point cloud data, particularly under conditions of extended distances and occlusions. Recently, temporal aggregation has been proven to significantly enhance detection accuracy by fusing multi-frame viewpoint information and enriching the spatial representation of objects. In this work, we introduce a novel LiDAR 3D object detection framework, namely LiSTM, to facilitate spatial-temporal feature learning with cross-frame motion forecasting information. We aim to improve the spatial-temporal interpretation capabilities of the LiDAR detector by incorporating a dynamic prior, generated from a non-learnable motion estimation model. Specifically, Motion-Guided Feature Aggregation (MGFA) is proposed to utilize the object trajectory from previous and future motion states to model spatial-temporal correlations into gaussian heatmap over a driving sequence. This motion-based heatmap then guides the temporal feature fusion, enriching the proposed object features. Moreover, we design a Dual Correlation Weighting Module (DCWM) that effectively facilitates the interaction between past and prospective frames through scene- and channel-wise feature abstraction. In the end, a cascade cross-attention-based decoder is employed to refine the 3D prediction. We have conducted experiments on the Waymo and nuScenes datasets to demonstrate that the proposed framework achieves superior 3D detection performance with effective spatial-temporal feature learning.		None
EgoHDM: An Online Egocentric-Inertial Human Motion Capture, Localization, and Dense Mapping System	2024-09-05	Show We present EgoHDM, an online egocentric-inertial human motion capture (mocap), localization, and dense mapping system. Our system uses 6 inertial measurement units (IMUs) and a commodity head-mounted RGB camera. EgoHDM is the first human mocap system that offers dense scene mapping in near real-time. Further, it is fast and robust to initialize and fully closes the loop between physically plausible map-aware global human motion estimation and mocap-aware 3D scene reconstruction. Our key idea is integrating camera localization and mapping information with inertial human motion capture bidirectionally in our system. To achieve this, we design a tightly coupled mocap-aware dense bundle adjustment and physics-based body pose correction module leveraging a local body-centric elevation map. The latter introduces a novel terrain-aware contact PD controller, which enables characters to physically contact the given local elevation map thereby reducing human floating or penetration. We demonstrate the performance of our system on established synthetic and real-world benchmarks. The results show that our method reduces human localization, camera pose, and mapping accuracy error by 41%, 71%, 46%, respectively, compared to the state of the art. Our qualitative evaluations on newly captured data further demonstrate that EgoHDM can cover challenging scenarios in non-flat terrain including stepping over stairs and outdoor scenes in the wild.	Proje... Project Page: https://handiyin.github.io/EgoHDM/	Code Link
MoManifold: Learning to Measure 3D Human Motion via Decoupled Joint Acceleration Manifolds	2024-09-01	Show Incorporating temporal information effectively is important for accurate 3D human motion estimation and generation which have wide applications from human-computer interaction to AR/VR. In this paper, we present MoManifold, a novel human motion prior, which models plausible human motion in continuous high-dimensional motion space. Different from existing mathematical or VAE-based methods, our representation is designed based on the neural distance field, which makes human dynamics explicitly quantified to a score and thus can measure human motion plausibility. Specifically, we propose novel decoupled joint acceleration manifolds to model human dynamics from existing limited motion data. Moreover, we introduce a novel optimization method using the manifold distance as guidance, which facilitates a variety of motion-related tasks. Extensive experiments demonstrate that MoManifold outperforms existing SOTAs as a prior in several downstream tasks such as denoising real-world human mocap data, recovering human motion from partial 3D observations, mitigating jitters for SMPL-based pose estimators, and refining the results of motion in-betweening.	Accep... Accepted by BMVC 2024. Supplementary material is included at the end of the main paper (12 pages, 11 figures, 5 tables)	None
xGen-VideoSyn-1: High-fidelity Text-to-Video Synthesis with Compressed Representations	2024-08-31	Show We present xGen-VideoSyn-1, a text-to-video (T2V) generation model capable of producing realistic scenes from textual descriptions. Building on recent advancements, such as OpenAI's Sora, we explore the latent diffusion model (LDM) architecture and introduce a video variational autoencoder (VidVAE). VidVAE compresses video data both spatially and temporally, significantly reducing the length of visual tokens and the computational demands associated with generating long-sequence videos. To further address the computational costs, we propose a divide-and-merge strategy that maintains temporal consistency across video segments. Our Diffusion Transformer (DiT) model incorporates spatial and temporal self-attention layers, enabling robust generalization across different timeframes and aspect ratios. We have devised a data processing pipeline from the very beginning and collected over 13M high-quality video-text pairs. The pipeline includes multiple steps such as clipping, text detection, motion estimation, aesthetics scoring, and dense captioning based on our in-house video-LLM model. Training the VidVAE and DiT models required approximately 40 and 642 H100 days, respectively. Our model supports over 14-second 720p video generation in an end-to-end way and demonstrates competitive performance against state-of-the-art T2V models.	Accep... Accepted by ECCV24 AI4VA	None
COIN: Control-Inpainting Diffusion Prior for Human and Camera Motion Estimation	2024-08-29	Show Estimating global human motion from moving cameras is challenging due to the entanglement of human and camera motions. To mitigate the ambiguity, existing methods leverage learned human motion priors, which however often result in oversmoothed motions with misaligned 2D projections. To tackle this problem, we propose COIN, a control-inpainting motion diffusion prior that enables fine-grained control to disentangle human and camera motions. Although pre-trained motion diffusion models encode rich motion priors, we find it non-trivial to leverage such knowledge to guide global motion estimation from RGB videos. COIN introduces a novel control-inpainting score distillation sampling method to ensure well-aligned, consistent, and high-quality motion from the diffusion prior within a joint optimization framework. Furthermore, we introduce a new human-scene relation loss to alleviate the scale ambiguity by enforcing consistency among the humans, camera, and scene. Experiments on three challenging benchmarks demonstrate the effectiveness of COIN, which outperforms the state-of-the-art methods in terms of global human motion estimation and camera motion estimation. As an illustrative example, COIN outperforms the state-of-the-art method by 33% in world joint position error (W-MPJPE) on the RICH dataset.	ECCV 2024	None
On the Benefits of Visual Stabilization for Frame- and Event-based Perception	2024-08-28	Show Vision-based perception systems are typically exposed to large orientation changes in different robot applications. In such conditions, their performance might be compromised due to the inherent complexity of processing data captured under challenging motion. Integration of mechanical stabilizers to compensate for the camera rotation is not always possible due to the robot payload constraints. This paper presents a processing-based stabilization approach to compensate the camera's rotational motion both on events and on frames (i.e., images). Assuming that the camera's attitude is available, we evaluate the benefits of stabilization in two perception applications: feature tracking and estimating the translation component of the camera's ego-motion. The validation is performed using synthetic data and sequences from well-known event-based vision datasets. The experiments unveil that stabilization can improve feature tracking and camera ego-motion estimation accuracy in 27.37% and 34.82%, respectively. Concurrently, stabilization can reduce the processing time of computing the camera's linear velocity by at least 25%. Code is available at https://github.com/tub-rip/visual_stabilization	8 pag... 8 pages, 4 figures, 4 tables, https://github.com/tub-rip/visual_stabilization	Code Link
RaNDT SLAM: Radar SLAM Based on Intensity-Augmented Normal Distributions Transform	2024-08-21	Show Rescue robotics sets high requirements to perception algorithms due to the unstructured and potentially vision-denied environments. Pivoting Frequency-Modulated Continuous Wave radars are an emerging sensing modality for SLAM in this kind of environment. However, the complex noise characteristics of radar SLAM makes, particularly indoor, applications computationally demanding and slow. In this work, we introduce a novel radar SLAM framework, RaNDT SLAM, that operates fast and generates accurate robot trajectories. The method is based on the Normal Distributions Transform augmented by radar intensity measures. Motion estimation is based on fusion of motion model, IMU data, and registration of the intensity-augmented Normal Distributions Transform. We evaluate RaNDT SLAM in a new benchmark dataset and the Oxford Radar RobotCar dataset. The new dataset contains indoor and outdoor environments besides multiple sensing modalities (LiDAR, radar, and IMU).	This ... This work was accepted by the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2024	None
Compression-Realized Deep Structural Network for Video Quality Enhancement	2024-08-20	Show This paper focuses on the task of quality enhancement for compressed videos. Although deep network-based video restorers achieve impressive progress, most of the existing methods lack a structured design to optimally leverage the priors within compression codecs. Since the quality degradation of the video is primarily induced by the compression algorithm, a new paradigm is urgently needed for a more ``conscious'' process of quality enhancement. As a result, we propose the Compression-Realized Deep Structural Network (CRDS), introducing three inductive biases aligned with the three primary processes in the classic compression codec, merging the strengths of classical encoder architecture with deep network capabilities. Inspired by the residual extraction and domain transformation process in the codec, a pre-trained Latent Degradation Residual Auto-Encoder is proposed to transform video frames into a latent feature space, and the mutual neighborhood attention mechanism is integrated for precise motion estimation and residual extraction. Furthermore, drawing inspiration from the quantization noise distribution of the codec, CRDS proposes a novel Progressive Denoising framework with intermediate supervision that decomposes the quality enhancement into a series of simpler denoising sub-tasks. Experimental results on datasets like LDV 2.0 and MFQE 2.0 indicate our approach surpasses state-of-the-art models.		None
OPPH: A Vision-Based Operator for Measuring Body Movements for Personal Healthcare	2024-08-18	Show Vision-based motion estimation methods show promise in accurately and unobtrusively estimating human body motion for healthcare purposes. However, these methods are not specifically designed for healthcare purposes and face challenges in real-world applications. Human pose estimation methods often lack the accuracy needed for detecting fine-grained, subtle body movements, while optical flow-based methods struggle with poor lighting conditions and unseen real-world data. These issues result in human body motion estimation errors, particularly during critical medical situations where the body is motionless, such as during unconsciousness. To address these challenges and improve the accuracy of human body motion estimation for healthcare purposes, we propose the OPPH operator designed to enhance current vision-based motion estimation methods. This operator, which considers human body movement and noise properties, functions as a multi-stage filter. Results tested on two real-world and one synthetic human motion dataset demonstrate that the operator effectively removes real-world noise, significantly enhances the detection of motionless states, maintains the accuracy of estimating active body movements, and maintains long-term body movement trends. This method could be beneficial for analyzing both critical medical events and chronic medical conditions.		None
Motion-compensated MR CINE reconstruction with reconstruction-driven motion estimation	2024-08-16	Show In cardiac CINE, motion-compensated MR reconstruction (MCMR) is an effective approach to address highly undersampled acquisitions by incorporating motion information between frames. In this work, we propose a novel perspective for addressing the MCMR problem and a more integrated and efficient solution to the MCMR field. Contrary to state-of-the-art (SOTA) MCMR methods which break the original problem into two sub-optimization problems, i.e. motion estimation and reconstruction, we formulate this problem as a single entity with one single optimization. Our approach is unique in that the motion estimation is directly driven by the ultimate goal, reconstruction, but not by the canonical motion-warping loss (similarity measurement between motion-warped images and target images). We align the objectives of motion estimation and reconstruction, eliminating the drawbacks of artifacts-affected motion estimation and therefore error-propagated reconstruction. Further, we can deliver high-quality reconstruction and realistic motion without applying any regularization/smoothness loss terms, circumventing the non-trivial weighting factor tuning. We evaluate our method on two datasets: 1) an in-house acquired 2D CINE dataset for the retrospective study and 2) the public OCMR cardiac dataset for the prospective study. The conducted experiments indicate that the proposed MCMR framework can deliver artifact-free motion estimation and high-quality MR images even for imaging accelerations up to 20x, outperforming SOTA non-MCMR and MCMR methods in both qualitative and quantitative evaluation across all experiments. The code is available at https://github.com/JZPeterPan/MCMR-Recon-Driven-Motion.		Code Link
Motion-aware Latent Diffusion Models for Video Frame Interpolation	2024-08-02	Show With the advancement of AIGC, video frame interpolation (VFI) has become a crucial component in existing video generation frameworks, attracting widespread research interest. For the VFI task, the motion estimation between neighboring frames plays a crucial role in avoiding motion ambiguity. However, existing VFI methods always struggle to accurately predict the motion information between consecutive frames, and this imprecise estimation leads to blurred and visually incoherent interpolated frames. In this paper, we propose a novel diffusion framework, motion-aware latent diffusion models (MADiff), which is specifically designed for the VFI task. By incorporating motion priors between the conditional neighboring frames with the target interpolated frame predicted throughout the diffusion sampling procedure, MADiff progressively refines the intermediate outcomes, culminating in generating both visually smooth and realistic results. Extensive experiments conducted on benchmark datasets demonstrate that our method achieves state-of-the-art performance significantly outperforming existing approaches, especially under challenging scenarios involving dynamic textures with complex motion.	17 pages, 4 figures	None
Structure from Motion-based Motion Estimation and 3D Reconstruction of Unknown Shaped Space Debris	2024-08-02	Show With the boost in the number of spacecraft launches in the current decades, the space debris problem is daily becoming significantly crucial. For sustainable space utilization, the continuous removal of space debris is the most severe problem for humanity. To maximize the reliability of the debris capture mission in orbit, accurate motion estimation of the target is essential. Space debris has lost its attitude and orbit control capabilities, and its shape is unknown due to the break. This paper proposes the Structure from Motion-based algorithm to perform unknown shaped space debris motion estimation with limited resources, where only 2D images are required as input. The method then outputs the reconstructed shape of the unknown object and the relative pose trajectory between the target and the camera simultaneously, which are exploited to estimate the target's motion. The method is quantitatively validated with the realistic image dataset generated by the microgravity experiment in a 2D air-floating testbed and 3D kinematic simulation.	6 pag... 6 pages, 10 figures. Manuscript accepted at the 2024 IEEE 20th International Conference on Automation Science and Engineerin (CASE 2024)	None
Neural Fields for Continuous Periodic Motion Estimation in 4D Cardiovascular Imaging	2024-07-30	Show Time-resolved three-dimensional flow MRI (4D flow MRI) provides a unique non-invasive solution to visualize and quantify hemodynamics in blood vessels such as the aortic arch. However, most current analysis methods for arterial 4D flow MRI use static artery walls because of the difficulty in obtaining a full cycle segmentation. To overcome this limitation, we propose a neural fields-based method that directly estimates continuous periodic wall deformations throughout the cardiac cycle. For a 3D + time imaging dataset, we optimize an implicit neural representation (INR) that represents a time-dependent velocity vector field (VVF). An ODE solver is used to integrate the VVF into a deformation vector field (DVF), that can deform images, segmentation masks, or meshes over time, thereby visualizing and quantifying local wall motion patterns. To properly reflect the periodic nature of 3D + time cardiovascular data, we impose periodicity in two ways. First, by periodically encoding the time input to the INR, and hence VVF. Second, by regularizing the DVF. We demonstrate the effectiveness of this approach on synthetic data with different periodic patterns, ECG-gated CT, and 4D flow MRI data. The obtained method could be used to improve 4D flow MRI analysis.	10 pa... 10 pages, 5 figures, STACOM 2024	None
Uniformly Accelerated Motion Model for Inter Prediction	2024-07-21	Show Inter prediction is a key technology to reduce the temporal redundancy in video coding. In natural videos, there are usually multiple moving objects with variable velocity, resulting in complex motion fields that are difficult to represent compactly. In Versatile Video Coding (VVC), existing inter prediction methods usually assume uniform speed motion between consecutive frames and use the linear models for motion estimation (ME) and motion compensation (MC), which may not well handle the complex motion fields in the real world. To address these issues, we introduce a uniformly accelerated motion model (UAMM) to exploit motion-related elements (velocity, acceleration) of moving objects between the video frames, and further combine them to assist the inter prediction methods to handle the variable motion in the temporal domain. Specifically, first, the theory of UAMM is mentioned. Second, based on that, we propose the UAMM-based parameter derivation and extrapolation schemes in the coding process. Third, we integrate the UAMM into existing inter prediction modes (Merge, MMVD, CIIP) to achieve higher prediction accuracy. The proposed method is implemented into the VVC reference software, VTM version 12.0. Experimental results show that the proposed method achieves up to 0.38% and on average 0.13% BD-rate reduction compared to the VTM anchor, under the Low-delay P configuration, with a slight increase of time complexity on the encoding/decoding side.	5 pages, 4 figures	None
A review on vision-based motion estimation	2024-07-19	Show Compared to contact sensors-based motion measurement, vision-based motion measurement has advantages of low cost and high efficiency and have been under active development in the past decades. This paper provides a review on existing motion measurement methods. In addition to the development of each branch of vision-based motion measurement methods, this paper also discussed the advantages and disadvantages of existing methods. Based on this discussion, it was identified that existing methods have a common limitation in optimally balancing accuracy and robustness. To address issue, we developed the Gaussian kernel-based motion measurement method. Preliminary study shows that the developed method can achieve high accuracy on simple synthesized images.	2 figures	None
Efficient and Safe Contact-rich pHRI via Subtask Detection and Motion Estimation using Deep Learning	2024-07-19	Show This paper proposes an adaptive admittance controller for improving efficiency and safety in physical human-robot interaction (pHRI) tasks in small-batch manufacturing that involve contact with stiff environments, such as drilling, polishing, cutting, etc. We aim to minimize human effort and task completion time while maximizing precision and stability during the contact of the machine tool attached to the robot's end-effector with the workpiece. To this end, a two-layered learning-based human intention recognition mechanism is proposed, utilizing only the kinematic and kinetic data from the robot and two force sensors. A subtask detector" recognizes the human intent by estimating which phase of the task is being performed, e.g., \textit{Idle}, \textit{Tool-Attachment}, \textit{Driving}, and \textit{Contact}. Simultaneously, a motion estimator" continuously quantifies intent more precisely during the \textit{Driving} to predict when \textit{Contact} will begin. The controller is adapted online according to the subtask while allowing early adaptation before the \textit{Contact} to maximize precision and safety and prevent potential instabilities. Three sets of pHRI experiments were performed with multiple subjects under various conditions. Spring compression experiments were performed in virtual environments to train the data-driven models and validate the proposed adaptive system, and drilling experiments were performed in the physical world to test the proposed methods' efficacy in real-life scenarios. Experimental results show subtask classification accuracy of 84% and motion estimation R\textsuperscript{2} score of 0.96. Furthermore, 57% lower human effort was achieved during \textit{Driving} as well as 53% lower oscillation amplitude at \textit{Contact} as a result of the proposed system.		None
Shape of Motion: 4D Reconstruction from a Single Video	2024-07-18	Show Monocular dynamic reconstruction is a challenging and long-standing vision problem due to the highly ill-posed nature of the task. Existing approaches are limited in that they either depend on templates, are effective only in quasi-static scenes, or fail to model 3D motion explicitly. In this work, we introduce a method capable of reconstructing generic dynamic scenes, featuring explicit, full-sequence-long 3D motion, from casually captured monocular videos. We tackle the under-constrained nature of the problem with two key insights: First, we exploit the low-dimensional structure of 3D motion by representing scene motion with a compact set of SE3 motion bases. Each point's motion is expressed as a linear combination of these bases, facilitating soft decomposition of the scene into multiple rigidly-moving groups. Second, we utilize a comprehensive set of data-driven priors, including monocular depth maps and long-range 2D tracks, and devise a method to effectively consolidate these noisy supervisory signals, resulting in a globally consistent representation of the dynamic scene. Experiments show that our method achieves state-of-the-art performance for both long-range 3D/2D motion estimation and novel view synthesis on dynamic scenes. Project Page: https://shape-of-motion.github.io/		None
Fusion LiDAR-Inertial-Encoder data for High-Accuracy SLAM	2024-07-17	Show In the realm of robotics, achieving simultaneous localization and mapping (SLAM) is paramount for autonomous navigation, especially in challenging environments like texture-less structures. This paper proposed a factor-graph-based model that tightly integrates IMU and encoder sensors to enhance positioning in such environments. The system operates by meticulously evaluating the data from each sensor. Based on these evaluations, weights are dynamically adjusted to prioritize the more reliable source of information at any given moment. The robot's state is initialized using IMU data, while the encoder aids motion estimation in long corridors. Discrepancies between the two states are used to correct IMU drift. The effectiveness of this method is demonstrably validated through experimentation. Compared to Karto SLAM, a widely used SLAM algorithm, this approach achieves an improvement of 26.98% in rotation angle error and 67.68% reduction in position error. These results convincingly demonstrate the method's superior accuracy and robustness in texture-less environments.	In th... In the 2024 International Conference on Mechatronic, Automobile, and Environment Engineering, Hanoi, Vietnam	None
Decomposition Betters Tracking Everything Everywhere	2024-07-16	Show Recent studies on motion estimation have advocated an optimized motion representation that is globally consistent across the entire video, preferably for every pixel. This is challenging as a uniform representation may not account for the complex and diverse motion and appearance of natural videos. We address this problem and propose a new test-time optimization method, named DecoMotion, for estimating per-pixel and long-range motion. DecoMotion explicitly decomposes video content into static scenes and dynamic objects, either of which uses a quasi-3D canonical volume to represent. DecoMotion separately coordinates the transformations between local and canonical spaces, facilitating an affine transformation for the static scene that corresponds to camera motion. For the dynamic volume, DecoMotion leverages discriminative and temporally consistent features to rectify the non-rigid transformation. The two volumes are finally fused to fully represent motion and appearance. This divide-and-conquer strategy leads to more robust tracking through occlusions and deformations and meanwhile obtains decomposed appearances. We conduct evaluations on the TAP-Vid benchmark. The results demonstrate our method boosts the point-tracking accuracy by a large margin and performs on par with some state-of-the-art dedicated point-tracking solutions.	ECCV ... ECCV 2024 Camera Ready. Code and models will be available at https://github.com/qianduoduolr/DecoMotion	Code Link
Motion-prior Contrast Maximization for Dense Continuous-Time Motion Estimation	2024-07-15	Show Current optical flow and point-tracking methods rely heavily on synthetic datasets. Event cameras are novel vision sensors with advantages in challenging visual conditions, but state-of-the-art frame-based methods cannot be easily adapted to event data due to the limitations of current event simulators. We introduce a novel self-supervised loss combining the Contrast Maximization framework with a non-linear motion prior in the form of pixel-level trajectories and propose an efficient solution to solve the high-dimensional assignment problem between non-linear trajectories and events. Their effectiveness is demonstrated in two scenarios: In dense continuous-time motion estimation, our method improves the zero-shot performance of a synthetically trained model on the real-world dataset EVIMO2 by 29%. In optical flow estimation, our method elevates a simple UNet to achieve state-of-the-art performance among self-supervised methods on the DSEC optical flow benchmark. Our code is available at https://github.com/tub-rip/MotionPriorCMax.	24 pa... 24 pages, 8 figures, 8 tables, Project Page: https://github.com/tub-rip/MotionPriorCMax	Code Link
SeSame: Simple, Easy 3D Object Detection with Point-Wise Semantics	2024-07-08	Show In autonomous driving, 3D object detection provides more precise information for downstream tasks, including path planning and motion estimation, compared to 2D object detection. In this paper, we propose SeSame: a method aimed at enhancing semantic information in existing LiDAR-only based 3D object detection. This addresses the limitation of existing 3D detectors, which primarily focus on object presence and classification, thus lacking in capturing relationships between elemental units that constitute the data, akin to semantic segmentation. Experiments demonstrate the effectiveness of our method with performance improvements on the KITTI object detection benchmark. Our code is available at https://github.com/HAMA-DL-dev/SeSame	17 pages, 4 figures	Code Link
LiDAR-based Real-Time Object Detection and Tracking in Dynamic Environments	2024-07-04	Show In dynamic environments, the ability to detect and track moving objects in real-time is crucial for autonomous robots to navigate safely and effectively. Traditional methods for dynamic object detection rely on high accuracy odometry and maps to detect and track moving objects. However, these methods are not suitable for long-term operation in dynamic environments where the surrounding environment is constantly changing. In order to solve this problem, we propose a novel system for detecting and tracking dynamic objects in real-time using only LiDAR data. By emphasizing the extraction of low-frequency components from LiDAR data as feature points for foreground objects, our method significantly reduces the time required for object clustering and movement analysis. Additionally, we have developed a tracking approach that employs intensity-based ego-motion estimation along with a sliding window technique to assess object movements. This enables the precise identification of moving objects and enhances the system's resilience to odometry drift. Our experiments show that this system can detect and track dynamic objects in real-time with an average detection accuracy of 88.7% and a recall rate of 89.1%. Furthermore, our system demonstrates resilience against the prolonged drift typically associated with front-end only LiDAR odometry. All of the source code, labeled dataset, and the annotation tool are available at: https://github.com/MISTLab/lidar_dynamic_objects_detection.git		Code Link
Speaker- and Text-Independent Estimation of Articulatory Movements and Phoneme Alignments from Speech	2024-07-03	Show This paper introduces a novel combination of two tasks, previously treated separately: acoustic-to-articulatory speech inversion (AAI) and phoneme-to-articulatory (PTA) motion estimation. We refer to this joint task as acoustic phoneme-to-articulatory speech inversion (APTAI) and explore two different approaches, both working speaker- and text-independently during inference. We use a multi-task learning setup, with the end-to-end goal of taking raw speech as input and estimating the corresponding articulatory movements, phoneme sequence, and phoneme alignment. While both proposed approaches share these same requirements, they differ in their way of achieving phoneme-related predictions: one is based on frame classification, the other on a two-staged training procedure and forced alignment. We reach competitive performance of 0.73 mean correlation for the AAI task and achieve up to approximately 87% frame overlap compared to a state-of-the-art text-dependent phoneme force aligner.	to be... to be published in Interspeech 2024 proceedings	None
Shakebot: A Low-cost, Open-source Robotic Shake Table for Earthquake Research and Education	2024-07-01	Show Shake tables serve as a critical tool for simulating earthquake events and testing the response of structures to seismic forces. However, existing shake tables are either expensive or proprietary. This paper presents the design and implementation of a low-cost, open-source shake table named \textit{Shakebot} for earthquake engineering research and education, built using Robot Operating System (ROS) and principles of robotics. The Shakebot adapts affordable and high-accuracy components from 3D printers, particularly a closed-loop stepper motor for actuation and a toothed belt for transmission. The stepper motor enables the bed to reach a maximum horizontal acceleration of 11.8 $m/s^2$ (1.2 $\mathbf{g}$), and velocity of 0.5 $m/s$, with a 2 $kg$ specimen. The Shakebot is equipped with an accelerometer and a high frame-rate camera for bed motion estimation. The low cost and easy use make the Shakebot accessible to a wide range of users, including students, educators, and researchers in resource-constrained settings. The Shakebot, along with its digital twin--a virtual shake robot--has showcased significant potential in advancing ground motion research. Specifically, this study examines the dynamics of precariously balanced rocks. The Shakebot provides an approach to validate the simulation through physical experiments. The ROS-based perception and motion software facilitates the code transition from our virtual shake robot to the physical Shakebot. The reuse of the control programs ensures that the implemented ground motions are consistent for both the simulation and physical experiments, which is critical to validate our simulation experiments.		None
IVCA: Inter-Relation-Aware Video Complexity Analyzer	2024-06-29	Show To meet the real-time analysis requirements of video streaming applications, we propose an inter-relation-aware video complexity analyzer (IVCA) as an extension to VCA. The IVCA addresses the limitation of VCA by considering inter-frame relations, namely motion and reference structure. First, we enhance the accuracy of temporal features by introducing feature-domain motion estimation into the IVCA. Next, drawing inspiration from the hierarchical reference structure in codecs, we design layer-aware weights to adjust the majorities of frame complexity in different layers. Additionally, we expand the scope of temporal features by considering frames that be referred to, rather than relying solely on the previous frame. Experimental results show the significant improvement in complexity estimation accuracy achieved by IVCA, with minimal time complexity increase.	The r... The report for the solution of second prize winner in ICIP 2024 Grand Challenge on Video Complexity (Team: USTC-iVC_Team1, USTC-iVC_Team2)	None
Continuous 3D Myocardial Motion Tracking via Echocardiography	2024-06-27	Show Myocardial motion tracking stands as an essential clinical tool in the prevention and detection of cardiovascular diseases (CVDs), the foremost cause of death globally. However, current techniques suffer from incomplete and inaccurate motion estimation of the myocardium in both spatial and temporal dimensions, hindering the early identification of myocardial dysfunction. To address these challenges, this paper introduces the Neural Cardiac Motion Field (NeuralCMF). NeuralCMF leverages implicit neural representation (INR) to model the 3D structure and the comprehensive 6D forward/backward motion of the heart. This method surpasses pixel-wise limitations by offering the capability to continuously query the precise shape and motion of the myocardium at any specific point throughout the cardiac cycle, enhancing the detailed analysis of cardiac dynamics beyond traditional speckle tracking. Notably, NeuralCMF operates without the need for paired datasets, and its optimization is self-supervised through the physics knowledge priors in both space and time dimensions, ensuring compatibility with both 2D and 3D echocardiogram video inputs. Experimental validations across three representative datasets support the robustness and innovative nature of the NeuralCMF, marking significant advantages over existing state-of-the-art methods in cardiac imaging and motion tracking.	18 pages, 11 figures	None
$D^2$SLAM: Decentralized and Distributed Collaborative Visual-inertial SLAM System for Aerial Swarm	2024-06-23	Show Collaborative simultaneous localization and mapping (CSLAM) is essential for autonomous aerial swarms, laying the foundation for downstream algorithms such as planning and control. To address existing CSLAM systems' limitations in relative localization accuracy, crucial for close-range UAV collaboration, this paper introduces $D^2$SLAM-a novel decentralized and distributed CSLAM system. $D^2$SLAM innovatively manages near-field estimation for precise relative state estimation in proximity and far-field estimation for consistent global trajectories. Its adaptable front-end supports both stereo and omnidirectional cameras, catering to various operational needs and overcoming field-of-view challenges in aerial swarms. Experiments demonstrate $D^2$SLAM's effectiveness in accurate ego-motion estimation, relative localization, and global consistency. Enhanced by distributed optimization algorithms, $D^2$SLAM exhibits remarkable scalability and resilience to network delays, making it well-suited for a wide range of real-world aerial swarm applications. The adaptability and proven performance of $D^2$SLAM represent a significant advancement in autonomous aerial swarm technology.	Submi... Submitted to IEEE Transaction on Robotics	None
MOWA: Multiple-in-One Image Warping Model	2024-06-17	Show While recent image warping approaches achieved remarkable success on existing benchmarks, they still require training separate models for each specific task and cannot generalize well to different camera models or customized manipulations. To address diverse types of warping in practice, we propose a Multiple-in-One image WArping model (named MOWA) in this work. Specifically, we mitigate the difficulty of multi-task learning by disentangling the motion estimation at both the region level and pixel level. To further enable dynamic task-aware image warping, we introduce a lightweight point-based classifier that predicts the task type, serving as prompts to modulate the feature maps for more accurate estimation. To our knowledge, this is the first work that solves multiple practical warping tasks in one single model. Extensive experiments demonstrate that our MOWA, which is trained on six tasks for multiple-in-one image warping, outperforms state-of-the-art task-specific models across most tasks. Moreover, MOWA also exhibits promising potential to generalize into unseen scenes, as evidenced by cross-domain and zero-shot evaluations. The code and more visual results can be found on the project page: https://kangliao929.github.io/projects/mowa/.	Proje... Project page: https://kangliao929.github.io/projects/mowa/	Code Link
oTTC: Object Time-to-Contact for Motion Estimation in Autonomous Driving	2024-05-13	Show Autonomous driving systems require a quick and robust perception of the nearby environment to carry out their routines effectively. With the aim to avoid collisions and drive safely, autonomous driving systems rely heavily on object detection. However, 2D object detections alone are insufficient; more information, such as relative velocity and distance, is required for safer planning. Monocular 3D object detectors try to solve this problem by directly predicting 3D bounding boxes and object velocities given a camera image. Recent research estimates time-to-contact in a per-pixel manner and suggests that it is more effective measure than velocity and depth combined. However, per-pixel time-to-contact requires object detection to serve its purpose effectively and hence increases overall computational requirements as two different models need to run. To address this issue, we propose per-object time-to-contact estimation by extending object detection models to additionally predict the time-to-contact attribute for each object. We compare our proposed approach with existing time-to-contact methods and provide benchmarking results on well-known datasets. Our proposed approach achieves higher precision compared to prior art while using a single image.	9 pages, 4 figures	None
Mocap Everyone Everywhere: Lightweight Motion Capture With Smartwatches and a Head-Mounted Camera	2024-05-06	Show We present a lightweight and affordable motion capture method based on two smartwatches and a head-mounted camera. In contrast to the existing approaches that use six or more expert-level IMU devices, our approach is much more cost-effective and convenient. Our method can make wearable motion capture accessible to everyone everywhere, enabling 3D full-body motion capture in diverse environments. As a key idea to overcome the extreme sparsity and ambiguities of sensor inputs with different modalities, we integrate 6D head poses obtained from the head-mounted cameras for motion estimation. To enable capture in expansive indoor and outdoor scenes, we propose an algorithm to track and update floor level changes to define head poses, coupled with a multi-stage Transformer-based regression module. We also introduce novel strategies leveraging visual cues of egocentric images to further enhance the motion capture quality while reducing ambiguities. We demonstrate the performance of our method on various challenging scenarios, including complex outdoor environments and everyday motions including object interactions and social interactions among multiple individuals.	Accep... Accepted to CVPR 2024; Project page: https://jiyewise.github.io/projects/MocapEvery/	Code Link
FlexKalmanNet: A Modular AI-Enhanced Kalman Filter Framework Applied to Spacecraft Motion Estimation	2024-05-05	Show The estimation of relative motion between spacecraft increasingly relies on feature-matching computer vision, which feeds data into a recursive filtering algorithm. Kalman filters, although efficient in noise compensation, demand extensive tuning of system and noise models. This paper introduces FlexKalmanNet, a novel modular framework that bridges this gap by integrating a deep fully connected neural network with Kalman filter-based motion estimation algorithms. FlexKalmanNet's core innovation is its ability to learn any Kalman filter parameter directly from measurement data, coupled with the flexibility to utilize various Kalman filter variants. This is achieved through a notable design decision to outsource the sequential computation from the neural network to the Kalman filter variant, enabling a purely feedforward neural network architecture. This architecture, proficient at handling complex, nonlinear features without the dependency on recurrent network modules, captures global data patterns more effectively. Empirical evaluation using data from NASA's Astrobee simulation environment focuses on learning unknown parameters of an Extended Kalman filter for spacecraft pose and twist estimation. The results demonstrate FlexKalmanNet's rapid training convergence, high accuracy, and superior performance against manually tuned Extended Kalman filters.		None
Instantaneous Perception of Moving Objects in 3D	2024-05-05	Show The perception of 3D motion of surrounding traffic participants is crucial for driving safety. While existing works primarily focus on general large motions, we contend that the instantaneous detection and quantification of subtle motions is equally important as they indicate the nuances in driving behavior that may be safety critical, such as behaviors near a stop sign of parking positions. We delve into this under-explored task, examining its unique challenges and developing our solution, accompanied by a carefully designed benchmark. Specifically, due to the lack of correspondences between consecutive frames of sparse Lidar point clouds, static objects might appear to be moving - the so-called swimming effect. This intertwines with the true object motion, thereby posing ambiguity in accurate estimation, especially for subtle motions. To address this, we propose to leverage local occupancy completion of object point clouds to densify the shape cue, and mitigate the impact of swimming artifacts. The occupancy completion is learned in an end-to-end fashion together with the detection of moving objects and the estimation of their motion, instantaneously as soon as objects start to move. Extensive experiments demonstrate superior performance compared to standard 3D motion estimation approaches, particularly highlighting our method's specialized treatment of subtle motions.	CVPR 2024	None
Enhancing Prosthetic Safety and Environmental Adaptability: A Visual-Inertial Prosthesis Motion Estimation Approach on Uneven Terrains	2024-04-29	Show Environment awareness is crucial for enhancing walking safety and stability of amputee wearing powered prosthesis when crossing uneven terrains such as stairs and obstacles. However, existing environmental perception systems for prosthesis only provide terrain types and corresponding parameters, which fails to prevent potential collisions when crossing uneven terrains and may lead to falls and other severe consequences. In this paper, a visual-inertial motion estimation approach is proposed for prosthesis to perceive its movement and the changes of spatial relationship between the prosthesis and uneven terrain when traversing them. To achieve this, we estimate the knee motion by utilizing a depth camera to perceive the environment and align feature points extracted from stairs and obstacles. Subsequently, an error-state Kalman filter is incorporated to fuse the inertial data into visual estimations to reduce the feature extraction error and obtain a more robust estimation. The motion of prosthetic joint and toe are derived using the prosthesis model parameters. Experiment conducted on our collected dataset and stair walking trials with a powered prosthesis shows that the proposed method can accurately tracking the motion of the human leg and prosthesis with an average root-mean-square error of toe trajectory less than 5 cm. The proposed method is expected to enable the environmental adaptive control for prosthesis, thereby enhancing amputee's safety and mobility in uneven terrains.		None
Development of an Estimation Method for the Seismic Motion Reproducibility of a Three-dimensional Ground Structure Model by combining Surface-observed Seismic Motion and Three-dimensional Seismic Motion Analysis	2024-04-27	Show The ground structure can substantially influence seismic ground motion underscoring the need to develop a ground structure model with sufficient reliability in terms of ground motion estimation for earthquake damage mitigation. While many methods for generating ground structure models have been proposed and used in practice, there remains room for enhancing their reliability. In this study, amid many candidate 3D ground structure models generated from geotechnical engineering knowledge, we propose a method for selecting a credible 3D ground structure model capable of reproducing observed earthquake ground motion, utilizing seismic ground motion data solely observed at the ground surface and employing 3D seismic ground motion analysis. Through a numerical experiment, we illustrate the efficacy of this approach. By conducting $10^2$-$10^3$ cases of fast 3D seismic wave propagation analyses using graphic processing units (GPUs), we demonstrate that a credible 3D ground structure model is selected according to the quantity of seismic motion information. We show the effectiveness of the proposed method by showing that the accuracy of seismic motions using ground structure models that were selected from the pool of candidate models is higher than that using ground structure models that were not selected from the pool of candidate models.	16 pa... 16 pages, 10 figures, accepted for IHPCES/ICCS 2024 (14th International Workshop on Advances in High-Performance Computational Earth Sciences: NumericalMethods, Frameworks & Applications / 24th International Conference on Computational Science)	None
Attention-aware non-rigid image registration for accelerated MR imaging	2024-04-26	Show Accurate motion estimation at high acceleration factors enables rapid motion-compensated reconstruction in Magnetic Resonance Imaging (MRI) without compromising the diagnostic image quality. In this work, we introduce an attention-aware deep learning-based framework that can perform non-rigid pairwise registration for fully sampled and accelerated MRI. We extract local visual representations to build similarity maps between the registered image pairs at multiple resolution levels and additionally leverage long-range contextual information using a transformer-based module to alleviate ambiguities in the presence of artifacts caused by undersampling. We combine local and global dependencies to perform simultaneous coarse and fine motion estimation. The proposed method was evaluated on in-house acquired fully sampled and accelerated data of 101 patients and 62 healthy subjects undergoing cardiac and thoracic MRI. The impact of motion estimation accuracy on the downstream task of motion-compensated reconstruction was analyzed. We demonstrate that our model derives reliable and consistent motion fields across different sampling trajectories (Cartesian and radial) and acceleration factors of up to 16x for cardiac motion and 30x for respiratory motion and achieves superior image quality in motion-compensated reconstruction qualitatively and quantitatively compared to conventional and recent deep learning-based approaches. The code is publicly available at https://github.com/lab-midas/GMARAFT.	14 pages, 7 figures	Code Link
Camera Motion Estimation from RGB-D-Inertial Scene Flow	2024-04-26	Show In this paper, we introduce a novel formulation for camera motion estimation that integrates RGB-D images and inertial data through scene flow. Our goal is to accurately estimate the camera motion in a rigid 3D environment, along with the state of the inertial measurement unit (IMU). Our proposed method offers the flexibility to operate as a multi-frame optimization or to marginalize older data, thus effectively utilizing past measurements. To assess the performance of our method, we conducted evaluations using both synthetic data from the ICL-NUIM dataset and real data sequences from the OpenLORIS-Scene dataset. Our results show that the fusion of these two sensors enhances the accuracy of camera motion estimation when compared to using only visual data.	Accep... Accepted to CVPR2024 Workshop on Visual Odometry and Computer Vision Applications	None
Vanishing-Point-Guided Video Semantic Segmentation of Driving Scenes	2024-04-26	Show The estimation of implicit cross-frame correspondences and the high computational cost have long been major challenges in video semantic segmentation (VSS) for driving scenes. Prior works utilize keyframes, feature propagation, or cross-frame attention to address these issues. By contrast, we are the first to harness vanishing point (VP) priors for more effective segmentation. Intuitively, objects near VPs (i.e., away from the vehicle) are less discernible. Moreover, they tend to move radially away from the VP over time in the usual case of a forward-facing camera, a straight road, and linear forward motion of the vehicle. Our novel, efficient network for VSS, named VPSeg, incorporates two modules that utilize exactly this pair of static and dynamic VP priors: sparse-to-dense feature mining (DenseVP) and VP-guided motion fusion (MotionVP). MotionVP employs VP-guided motion estimation to establish explicit correspondences across frames and help attend to the most relevant features from neighboring frames, while DenseVP enhances weak dynamic features in distant regions around VPs. These modules operate within a context-detail framework, which separates contextual features from high-resolution local features at different input resolutions to reduce computational costs. Contextual and local features are integrated through contextualized motion attention (CMA) for the final prediction. Extensive experiments on two popular driving segmentation benchmarks, Cityscapes and ACDC, demonstrate that VPSeg outperforms previous SOTA methods, with only modest computational overhead.	CVPR 2024 highlight	None
Multimotion Visual Odometry (MVO)	2024-04-23	Show Visual motion estimation is a well-studied challenge in autonomous navigation. Recent work has focused on addressing multimotion estimation in highly dynamic environments. These environments not only comprise multiple, complex motions but also tend to exhibit significant occlusion. Estimating third-party motions simultaneously with the sensor egomotion is difficult because an object's observed motion consists of both its true motion and the sensor motion. Most previous works in multimotion estimation simplify this problem by relying on appearance-based object detection or application-specific motion constraints. These approaches are effective in specific applications and environments but do not generalize well to the full multimotion estimation problem (MEP). This paper presents Multimotion Visual Odometry (MVO), a multimotion estimation pipeline that estimates the full SE(3) trajectory of every motion in the scene, including the sensor egomotion, without relying on appearance-based information. MVO extends the traditional visual odometry (VO) pipeline with multimotion segmentation and tracking techniques. It uses physically founded motion priors to extrapolate motions through temporary occlusions and identify the reappearance of motions through motion closure. Evaluations on real-world data from the Oxford Multimotion Dataset (OMD) and the KITTI Vision Benchmark Suite demonstrate that MVO achieves good estimation accuracy compared to similar approaches and is applicable to a variety of multimotion estimation challenges.	25 pa... 25 pages, 15 figures, 11 tables. Videos available at https://www.youtube.com/watch?v=mNj3s1nf-6A and https://www.youtube.com/playlist?list=PLbaQBz4TuPcxMIXKh5Q80s0N9ISezFcpi	None
RMS: Redundancy-Minimizing Point Cloud Sampling for Real-Time Pose Estimation	2024-04-23	Show The typical point cloud sampling methods used in state estimation for mobile robots preserve a high level of point redundancy. This redundancy unnecessarily slows down the estimation pipeline and may cause drift under real-time constraints. Such undue latency becomes a bottleneck for resource-constrained robots (especially UAVs), requiring minimal delay for agile and accurate operation. We propose a novel, deterministic, uninformed, and single-parameter point cloud sampling method named RMS that minimizes redundancy within a 3D point cloud. In contrast to the state of the art, RMS balances the translation-space observability by leveraging the fact that linear and planar surfaces inherently exhibit high redundancy propagated into iterative estimation pipelines. We define the concept of gradient flow, quantifying the local surface underlying a point. We also show that maximizing the entropy of the gradient flow minimizes point redundancy for robot ego-motion estimation. We integrate RMS into the point-based KISS-ICP and feature-based LOAM odometry pipelines and evaluate experimentally on KITTI, Hilti-Oxford, and custom datasets from multirotor UAVs. The experiments demonstrate that RMS outperforms state-of-the-art methods in speed, compression, and accuracy in well-conditioned as well as in geometrically-degenerated settings.	Accep... Accepted to IEEE RA-L on March 31, 2024	None
Mining Supervision for Dynamic Regions in Self-Supervised Monocular Depth Estimation	2024-04-23	Show This paper focuses on self-supervised monocular depth estimation in dynamic scenes trained on monocular videos. Existing methods jointly estimate pixel-wise depth and motion, relying mainly on an image reconstruction loss. Dynamic regions1 remain a critical challenge for these methods due to the inherent ambiguity in depth and motion estimation, resulting in inaccurate depth estimation. This paper proposes a self-supervised training framework exploiting pseudo depth labels for dynamic regions from training data. The key contribution of our framework is to decouple depth estimation for static and dynamic regions of images in the training data. We start with an unsupervised depth estimation approach, which provides reliable depth estimates for static regions and motion cues for dynamic regions and allows us to extract moving object information at the instance level. In the next stage, we use an object network to estimate the depth of those moving objects assuming rigid motions. Then, we propose a new scale alignment module to address the scale ambiguity between estimated depths for static and dynamic regions. We can then use the depth labels generated to train an end-to-end depth estimation network and improve its performance. Extensive experiments on the Cityscapes and KITTI datasets show that our self-training strategy consistently outperforms existing self/unsupervised depth estimation methods.	Accepted to CVPR2024	None
PeLiCal: Targetless Extrinsic Calibration via Penetrating Lines for RGB-D Cameras with Limited Co-visibility	2024-04-23	Show RGB-D cameras are crucial in robotic perception, given their ability to produce images augmented with depth data. However, their limited FOV often requires multiple cameras to cover a broader area. In multi-camera RGB-D setups, the goal is typically to reduce camera overlap, optimizing spatial coverage with as few cameras as possible. The extrinsic calibration of these systems introduces additional complexities. Existing methods for extrinsic calibration either necessitate specific tools or highly depend on the accuracy of camera motion estimation. To address these issues, we present PeLiCal, a novel line-based calibration approach for RGB-D camera systems exhibiting limited overlap. Our method leverages long line features from surroundings, and filters out outliers with a novel convergence voting algorithm, achieving targetless, real-time, and outlier-robust performance compared to existing methods. We open source our implementation on https://github.com/joomeok/PeLiCal.git.		Code Link
3DFlowRenderer: One-shot Face Re-enactment via Dense 3D Facial Flow Estimation	2024-04-23	Show Performing facial expression transfer under one-shot setting has been increasing in popularity among research community with a focus on precise control of expressions. Existing techniques showcase compelling results in perceiving expressions, but they lack robustness with extreme head poses. They also struggle to accurately reconstruct background details, thus hindering the realism. In this paper, we propose a novel warping technology which integrates the advantages of both 2D and 3D methods to achieve robust face re-enactment. We generate dense 3D facial flow fields in feature space to warp an input image based on target expressions without depth information. This enables explicit 3D geometric control for re-enacting misaligned source and target faces. We regularize the motion estimation capability of the 3D flow prediction network through proposed "Cyclic warp loss" by converting warped 3D features back into 2D RGB space. To ensure the generation of finer facial region with natural-background, our framework only renders the facial foreground region first and learns to inpaint the blank area which needs to be filled due to source face translation, thus reconstructing the detailed background without any unwanted pixel motion. Extensive evaluation reveals that our method outperforms state-of-the-art techniques in rendering artifact-free facial images.		None
Motion-adaptive Separable Collaborative Filters for Blind Motion Deblurring	2024-04-19	Show Eliminating image blur produced by various kinds of motion has been a challenging problem. Dominant approaches rely heavily on model capacity to remove blurring by reconstructing residual from blurry observation in feature space. These practices not only prevent the capture of spatially variable motion in the real world but also ignore the tailored handling of various motions in image space. In this paper, we propose a novel real-world deblurring filtering model called the Motion-adaptive Separable Collaborative (MISC) Filter. In particular, we use a motion estimation network to capture motion information from neighborhoods, thereby adaptively estimating spatially-variant motion flow, mask, kernels, weights, and offsets to obtain the MISC Filter. The MISC Filter first aligns the motion-induced blurring patterns to the motion middle along the predicted flow direction, and then collaboratively filters the aligned image through the predicted kernels, weights, and offsets to generate the output. This design can handle more generalized and complex motion in a spatially differentiated manner. Furthermore, we analyze the relationships between the motion estimation network and the residual reconstruction network. Extensive experiments on four widely used benchmarks demonstrate that our method provides an effective solution for real-world motion blur removal and achieves state-of-the-art performance. Code is available at https://github.com/ChengxuLiu/MISCFilter	CVPR 2024	Code Link
MultiPhys: Multi-Person Physics-aware 3D Motion Estimation	2024-04-18	Show We introduce MultiPhys, a method designed for recovering multi-person motion from monocular videos. Our focus lies in capturing coherent spatial placement between pairs of individuals across varying degrees of engagement. MultiPhys, being physically aware, exhibits robustness to jittering and occlusions, and effectively eliminates penetration issues between the two individuals. We devise a pipeline in which the motion estimated by a kinematic-based method is fed into a physics simulator in an autoregressive manner. We introduce distinct components that enable our model to harness the simulator's properties without compromising the accuracy of the kinematic estimates. This results in final motion estimates that are both kinematically coherent and physically compliant. Extensive evaluations on three challenging datasets characterized by substantial inter-person interaction show that our method significantly reduces errors associated with penetration and foot skating, while performing competitively with the state-of-the-art on motion accuracy and smoothness. Results and code can be found on our project page (http://www.iri.upc.edu/people/nugrinovic/multiphys/).		None
Dynamic Ego-Velocity estimation Using Moving mmWave Radar: A Phase-Based Approach	2024-04-15	Show Precise ego-motion measurement is crucial for various applications, including robotics, augmented reality, and autonomous navigation. In this poster, we propose mmPhase, an odometry framework based on single-chip millimetre-wave (mmWave) radar for robust ego-motion estimation in mobile platforms without requiring additional modalities like the visual, wheel, or inertial odometry. mmPhase leverages a phase-based velocity estimation approach to overcome the limitations of conventional doppler resolution. For real-world evaluations of mmPhase we have developed an ego-vehicle prototype. Compared to the state-of-the-art baselines, mmPhase shows superior performance in ego-velocity estimation.		None
GAN-based iterative motion estimation in HASTE MRI	2024-04-11	Show Magnetic Resonance Imaging allows high resolution data acquisition with the downside of motion sensitivity due to relatively long acquisition times. Even during the acquisition of a single 2D slice, motion can severely corrupt the image. Retrospective motion correction strategies do not interfere during acquisition time but operate on the motion affected data. Known methods suited to this scenario are compressed sensing (CS), generative adversarial networks (GANs), and explicit motion estimation. In this paper we propose an iterative approach which uses GAN predictions for motion estimation. The motion estimates allow to provide data consistent reconstructions and can improve reconstruction quality and reliability. With this approach, a clinical application of motion estimation is feasible without any further requirements on the acquisition trajectory i.e. no temporal redundancy is needed. We evaluate our proposed supervised network on motion corrupted HASTE acquisitions of brain and abdomen.	13 pa... 13 pages, 6 figures, 2 tables	None
Perception-Oriented Video Frame Interpolation via Asymmetric Blending	2024-04-10	Show Previous methods for Video Frame Interpolation (VFI) have encountered challenges, notably the manifestation of blur and ghosting effects. These issues can be traced back to two pivotal factors: unavoidable motion errors and misalignment in supervision. In practice, motion estimates often prove to be error-prone, resulting in misaligned features. Furthermore, the reconstruction loss tends to bring blurry results, particularly in misaligned regions. To mitigate these challenges, we propose a new paradigm called PerVFI (Perception-oriented Video Frame Interpolation). Our approach incorporates an Asymmetric Synergistic Blending module (ASB) that utilizes features from both sides to synergistically blend intermediate features. One reference frame emphasizes primary content, while the other contributes complementary information. To impose a stringent constraint on the blending process, we introduce a self-learned sparse quasi-binary mask which effectively mitigates ghosting and blur artifacts in the output. Additionally, we employ a normalizing flow-based generator and utilize the negative log-likelihood loss to learn the conditional distribution of the output, which further facilitates the generation of clear and fine details. Experimental results validate the superiority of PerVFI, demonstrating significant improvements in perceptual quality compared to existing methods. Codes are available at \url{https://github.com/mulns/PerVFI}	Accep... Accepted by CVPR 2024	Code Link
Space-Time Video Super-resolution with Neural Operator	2024-04-09	Show This paper addresses the task of space-time video super-resolution (ST-VSR). Existing methods generally suffer from inaccurate motion estimation and motion compensation (MEMC) problems for large motions. Inspired by recent progress in physics-informed neural networks, we model the challenges of MEMC in ST-VSR as a mapping between two continuous function spaces. Specifically, our approach transforms independent low-resolution representations in the coarse-grained continuous function space into refined representations with enriched spatiotemporal details in the fine-grained continuous function space. To achieve efficient and accurate MEMC, we design a Galerkin-type attention function to perform frame alignment and temporal interpolation. Due to the linear complexity of the Galerkin-type attention mechanism, our model avoids patch partitioning and offers global receptive fields, enabling precise estimation of large motions. The experimental results show that the proposed method surpasses state-of-the-art techniques in both fixed-size and continuous space-time video super-resolution tasks.		None
A Unified Diffusion Framework for Scene-aware Human Motion Estimation from Sparse Signals	2024-04-07	Show Estimating full-body human motion via sparse tracking signals from head-mounted displays and hand controllers in 3D scenes is crucial to applications in AR/VR. One of the biggest challenges to this task is the one-to-many mapping from sparse observations to dense full-body motions, which endowed inherent ambiguities. To help resolve this ambiguous problem, we introduce a new framework to combine rich contextual information provided by scenes to benefit full-body motion tracking from sparse observations. To estimate plausible human motions given sparse tracking signals and 3D scenes, we develop $\text{S}^2$Fusion, a unified framework fusing \underline{S}cene and sparse \underline{S}ignals with a conditional dif\underline{Fusion} model. $\text{S}^2$Fusion first extracts the spatial-temporal relations residing in the sparse signals via a periodic autoencoder, and then produces time-alignment feature embedding as additional inputs. Subsequently, by drawing initial noisy motion from a pre-trained prior, $\text{S}^2$Fusion utilizes conditional diffusion to fuse scene geometry and sparse tracking signals to generate full-body scene-aware motions. The sampling procedure of $\text{S}^2$Fusion is further guided by a specially designed scene-penetration loss and phase-matching loss, which effectively regularizes the motion of the lower body even in the absence of any tracking signals, making the generated motion much more plausible and coherent. Extensive experimental results have demonstrated that our $\text{S}^2$Fusion outperforms the state-of-the-art in terms of estimation quality and smoothness.		None
PhysPT: Physics-aware Pretrained Transformer for Estimating Human Dynamics from Monocular Videos	2024-04-05	Show While current methods have shown promising progress on estimating 3D human motion from monocular videos, their motion estimates are often physically unrealistic because they mainly consider kinematics. In this paper, we introduce Physics-aware Pretrained Transformer (PhysPT), which improves kinematics-based motion estimates and infers motion forces. PhysPT exploits a Transformer encoder-decoder backbone to effectively learn human dynamics in a self-supervised manner. Moreover, it incorporates physics principles governing human motion. Specifically, we build a physics-based body representation and contact force model. We leverage them to impose novel physics-inspired training losses (i.e., force loss, contact loss, and Euler-Lagrange loss), enabling PhysPT to capture physical properties of the human body and the forces it experiences. Experiments demonstrate that, once trained, PhysPT can be directly applied to kinematics-based estimates to significantly enhance their physical plausibility and generate favourable motion forces. Furthermore, we show that these physically meaningful quantities translate into improved accuracy of an important downstream task: human action recognition.		None
Advancements in Radar Odometry	2024-04-05	Show Radar odometry estimation has emerged as a critical technique in the field of autonomous navigation, providing robust and reliable motion estimation under various environmental conditions. Despite its potential, the complex nature of radar signals and the inherent challenges associated with processing these signals have limited the widespread adoption of this technology. This paper aims to address these challenges by proposing novel improvements to an existing method for radar odometry estimation, designed to enhance accuracy and reliability in diverse scenarios. Our pipeline consists of filtering, motion compensation, oriented surface points computation, smoothing, one-to-many radar scan registration, and pose refinement. The developed method enforces local understanding of the scene, by adding additional information through smoothing techniques, and alignment of consecutive scans, as a refinement posterior to the one-to-many registration. We present an in-depth investigation of the contribution of each improvement to the localization accuracy, and we benchmark our system on the sequences of the main datasets for radar understanding, i.e., the Oxford Radar RobotCar, MulRan, and Boreas datasets. The proposed pipeline is able to achieve superior results, on all scenarios considered and under harsh environmental constraints.		None
An N-Point Linear Solver for Line and Motion Estimation with Event Cameras	2024-04-01	Show Event cameras respond primarily to edges--formed by strong gradients--and are thus particularly well-suited for line-based motion estimation. Recent work has shown that events generated by a single line each satisfy a polynomial constraint which describes a manifold in the space-time volume. Multiple such constraints can be solved simultaneously to recover the partial linear velocity and line parameters. In this work, we show that, with a suitable line parametrization, this system of constraints is actually linear in the unknowns, which allows us to design a novel linear solver. Unlike existing solvers, our linear solver (i) is fast and numerically stable since it does not rely on expensive root finding, (ii) can solve both minimal and overdetermined systems with more than 5 events, and (iii) admits the characterization of all degenerate cases and multiple solutions. The found line parameters are singularity-free and have a fixed scale, which eliminates the need for auxiliary constraints typically encountered in previous work. To recover the full linear camera velocity we fuse observations from multiple lines with a novel velocity averaging scheme that relies on a geometrically-motivated residual, and thus solves the problem more efficiently than previous schemes which minimize an algebraic residual. Extensive experiments in synthetic and real-world settings demonstrate that our method surpasses the previous work in numerical stability, and operates over 600 times faster.		None
2D Ego-Motion with Yaw Estimation using Only mmWave Radars via Two-Way weighted ICP	2024-03-31	Show The interest in single-chip mmWave Radar is driven by their compact form factor, cost-effectiveness, and robustness under harsh environmental conditions. Despite its promising attributes, the principal limitation of mmWave radar lies in its capacity for autonomous yaw rate estimation. Conventional solutions have often resorted to integrating inertial measurement unit (IMU) or deploying multiple radar units to circumvent this shortcoming. This paper introduces an innovative methodology for two-dimensional ego-motion estimation, focusing on yaw rate deduction, utilizing solely mmWave radar sensors. By applying a weighted Iterated Closest Point (ICP) algorithm to register processed points derived from heatmap data, our method facilitates 2D ego-motion estimation devoid of prior information. Through experimental validation, we verified the effectiveness and promise of our technique for ego-motion estimation using exclusively radar data.		None
GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians	2024-03-30	Show We present GaussianAvatar, an efficient approach to creating realistic human avatars with dynamic 3D appearances from a single video. We start by introducing animatable 3D Gaussians to explicitly represent humans in various poses and clothing styles. Such an explicit and animatable representation can fuse 3D appearances more efficiently and consistently from 2D observations. Our representation is further augmented with dynamic properties to support pose-dependent appearance modeling, where a dynamic appearance network along with an optimizable feature tensor is designed to learn the motion-to-appearance mapping. Moreover, by leveraging the differentiable motion condition, our method enables a joint optimization of motions and appearances during avatar modeling, which helps to tackle the long-standing issue of inaccurate motion estimation in monocular settings. The efficacy of GaussianAvatar is validated on both the public dataset and our collected dataset, demonstrating its superior performances in terms of appearance quality and rendering efficiency.	Proje... Project Page: https://huliangxiao.github.io/GaussianAvatar	Code Link
Uncertainty-Aware Deep Video Compression with Ensembles	2024-03-28	Show Deep learning-based video compression is a challenging task, and many previous state-of-the-art learning-based video codecs use optical flows to exploit the temporal correlation between successive frames and then compress the residual error. Although these two-stage models are end-to-end optimized, the epistemic uncertainty in the motion estimation and the aleatoric uncertainty from the quantization operation lead to errors in the intermediate representations and introduce artifacts in the reconstructed frames. This inherent flaw limits the potential for higher bit rate savings. To address this issue, we propose an uncertainty-aware video compression model that can effectively capture the predictive uncertainty with deep ensembles. Additionally, we introduce an ensemble-aware loss to encourage the diversity among ensemble members and investigate the benefits of incorporating adversarial training in the video compression task. Experimental results on 1080p sequences show that our model can effectively save bits by more than 20% compared to DVC Pro.	Publi... Published on IEEE Transactions on Multimedia	None
iSLAM: Imperative SLAM	2024-03-22	Show Simultaneous Localization and Mapping (SLAM) stands as one of the critical challenges in robot navigation. A SLAM system often consists of a front-end component for motion estimation and a back-end system for eliminating estimation drifts. Recent advancements suggest that data-driven methods are highly effective for front-end tasks, while geometry-based methods continue to be essential in the back-end processes. However, such a decoupled paradigm between the data-driven front-end and geometry-based back-end can lead to sub-optimal performance, consequently reducing the system's capabilities and generalization potential. To solve this problem, we proposed a novel self-supervised imperative learning framework, named imperative SLAM (iSLAM), which fosters reciprocal correction between the front-end and back-end, thus enhancing performance without necessitating any external supervision. Specifically, we formulate the SLAM problem as a bilevel optimization so that the front-end and back-end are bidirectionally connected. As a result, the front-end model can learn global geometric knowledge obtained through pose graph optimization by back-propagating the residuals from the back-end component. We showcase the effectiveness of this new framework through an application of stereo-inertial SLAM. The experiments show that the iSLAM training strategy achieves an accuracy improvement of 22% on average over a baseline model. To the best of our knowledge, iSLAM is the first SLAM system showing that the front-end and back-end components can mutually correct each other in a self-supervised manner.	The p... The paper has been accepted by IEEE Robotics and Automation Letters (RA-L)	None
DD-VNB: A Depth-based Dual-Loop Framework for Real-time Visually Navigated Bronchoscopy	2024-03-15	Show Real-time 6 DOF localization of bronchoscopes is crucial for enhancing intervention quality. However, current vision-based technologies struggle to balance between generalization to unseen data and computational speed. In this study, we propose a Depth-based Dual-Loop framework for real-time Visually Navigated Bronchoscopy (DD-VNB) that can generalize across patient cases without the need of re-training. The DD-VNB framework integrates two key modules: depth estimation and dual-loop localization. To address the domain gap among patients, we propose a knowledge-embedded depth estimation network that maps endoscope frames to depth, ensuring generalization by eliminating patient-specific textures. The network embeds view synthesis knowledge into a cycle adversarial architecture for scale-constrained monocular depth estimation. For real-time performance, our localization module embeds a fast ego-motion estimation network into the loop of depth registration. The ego-motion inference network estimates the pose change of the bronchoscope in high frequency while depth registration against the pre-operative 3D model provides absolute pose periodically. Specifically, the relative pose changes are fed into the registration process as the initial guess to boost its accuracy and speed. Experiments on phantom and in-vivo data from patients demonstrate the effectiveness of our framework: 1) monocular depth estimation outperforms SOTA, 2) localization achieves an accuracy of Absolute Tracking Error (ATE) of 4.7 $\pm$ 3.17 mm in phantom and 6.49 $\pm$ 3.88 mm in patient data, 3) with a frame-rate approaching video capture speed, 4) without the necessity of case-wise network retraining. The framework's superior speed and accuracy demonstrate its promising clinical potential for real-time bronchoscopic navigation.		None
IBVC: Interpolation-driven B-frame Video Compression	2024-03-14	Show Learned B-frame video compression aims to adopt bi-directional motion estimation and motion compensation (MEMC) coding for middle frame reconstruction. However, previous learned approaches often directly extend neural P-frame codecs to B-frame relying on bi-directional optical-flow estimation or video frame interpolation. They suffer from inaccurate quantized motions and inefficient motion compensation. To address these issues, we propose a simple yet effective structure called Interpolation-driven B-frame Video Compression (IBVC). Our approach only involves two major operations: video frame interpolation and artifact reduction compression. IBVC introduces a bit-rate free MEMC based on interpolation, which avoids optical-flow quantization and additional compression distortions. Later, to reduce duplicate bit-rate consumption and focus on unaligned artifacts, a residual guided masking encoder is deployed to adaptively select the meaningful contexts with interpolated multi-scale dependencies. In addition, a conditional spatio-temporal decoder is proposed to eliminate location errors and artifacts instead of using MEMC coding in other methods. The experimental results on B-frame coding demonstrate that IBVC has significant improvements compared to the relevant state-of-the-art methods. Meanwhile, our approach can save bit rates compared with the random access (RA) configuration of H.266 (VTM). The code will be available at https://github.com/ruhig6/IBVC.	Submi... Submitted to Pattern Recognition	Code Link
Dynamic computerized tomography using inexact models and motion estimation	2024-03-13	Show Reconstructing a dynamic object with affine motion in computerized tomography (CT) leads to motion artifacts if the motion is not taken into account. In most cases, the actual motion is neither known nor can be determined easily. As a consequence, the respective model that describes CT is incomplete. The iterative RESESOP-Kaczmarz method can - under certain conditions and by exploiting the modeling error - reconstruct dynamic objects at different time points even if the exact motion is unknown. However, the method is very time-consuming. To speed the reconstruction process up and obtain better results, we combine the following three steps: 1. RESESOP-Kacmarz with only a few iterations is implemented to reconstruct the object at different time points. 2. The motion is estimated via landmark detection, e.g. using deep learning. 3. The estimated motion is integrated into the reconstruction process, allowing the use of dynamic filtered backprojection. We give a short review of all methods involved and present numerical results as a proof of principle.	21 pages, 9 figures	None
CMax-SLAM: Event-based Rotational-Motion Bundle Adjustment and SLAM System using Contrast Maximization	2024-03-12	Show Event cameras are bio-inspired visual sensors that capture pixel-wise intensity changes and output asynchronous event streams. They show great potential over conventional cameras to handle challenging scenarios in robotics and computer vision, such as high-speed and high dynamic range. This paper considers the problem of rotational motion estimation using event cameras. Several event-based rotation estimation methods have been developed in the past decade, but their performance has not been evaluated and compared under unified criteria yet. In addition, these prior works do not consider a global refinement step. To this end, we conduct a systematic study of this problem with two objectives in mind: summarizing previous works and presenting our own solution. First, we compare prior works both theoretically and experimentally. Second, we propose the first event-based rotation-only bundle adjustment (BA) approach. We formulate it leveraging the state-of-the-art Contrast Maximization (CMax) framework, which is principled and avoids the need to convert events into frames. Third, we use the proposed BA to build CMax-SLAM, the first event-based rotation-only SLAM system comprising a front-end and a back-end. Our BA is able to run both offline (trajectory smoothing) and online (CMax-SLAM back-end). To demonstrate the performance and versatility of our method, we present comprehensive experiments on synthetic and real-world datasets, including indoor, outdoor and space scenarios. We discuss the pitfalls of real-world evaluation and propose a proxy for the reprojection error as the figure of merit to evaluate event-based rotation BA methods. We release the source code and novel data sequences to benefit the community. We hope this work leads to a better understanding and fosters further research on event-based ego-motion estimation. Project page: https://github.com/tub-rip/cmax_slam	22 pa... 22 pages, 20 figures, 8 tables. https://github.com/tub-rip/cmax_slam	Code Link
RaTrack: Moving Object Detection and Tracking with 4D Radar Point Cloud	2024-03-11	Show Mobile autonomy relies on the precise perception of dynamic environments. Robustly tracking moving objects in 3D world thus plays a pivotal role for applications like trajectory prediction, obstacle avoidance, and path planning. While most current methods utilize LiDARs or cameras for Multiple Object Tracking (MOT), the capabilities of 4D imaging radars remain largely unexplored. Recognizing the challenges posed by radar noise and point sparsity in 4D radar data, we introduce RaTrack, an innovative solution tailored for radar-based tracking. Bypassing the typical reliance on specific object types and 3D bounding boxes, our method focuses on motion segmentation and clustering, enriched by a motion estimation module. Evaluated on the View-of-Delft dataset, RaTrack showcases superior tracking precision of moving objects, largely surpassing the performance of the state of the art. We release our code and model at https://github.com/LJacksonPan/RaTrack.	Accep... Accepted to ICRA 2024. 8 pages, 4 figures. Co-first authorship for Zhijun Pan, Fangqiang Ding and Hantao Zhong, listed randomly. See demo vide at: https://www.youtube.com/watch?v=_uSpbxOlLGw	Code Link
Exploiting polar symmetry in designing equivariant observers for vision-based motion estimation	2024-03-11	Show Accurately estimating camera motion from image sequences poses a significant challenge in computer vision and robotics. Many computer vision methods first compute the essential matrix associated with a motion and then extract orientation and normalized translation as inputs to pose estimation, reconstructing the scene scale (that is unobservable in the epipolar construction) from separate information. In this paper, we design a continuous-time filter that exploits the same perspective by using the epipolar constraint to define pseudo-measurements. We propose a novel polar symmetry on the pose of the camera that makes these measurements equivariant. This allows us to apply recent results from equivariant systems theory to estimating pose. We provide a novel explicit persistence of excitation condition to characterize observability of the full pose, ensuring reconstruction of the scale parameter that is not directly observable in the epipolar construction.	Preprint for L-CSS	None
DO3D: Self-supervised Learning of Decomposed Object-aware 3D Motion and Depth from Monocular Videos	2024-03-09	Show Although considerable advancements have been attained in self-supervised depth estimation from monocular videos, most existing methods often treat all objects in a video as static entities, which however violates the dynamic nature of real-world scenes and fails to model the geometry and motion of moving objects. In this paper, we propose a self-supervised method to jointly learn 3D motion and depth from monocular videos. Our system contains a depth estimation module to predict depth, and a new decomposed object-wise 3D motion (DO3D) estimation module to predict ego-motion and 3D object motion. Depth and motion networks work collaboratively to faithfully model the geometry and dynamics of real-world scenes, which, in turn, benefits both depth and 3D motion estimation. Their predictions are further combined to synthesize a novel video frame for self-supervised training. As a core component of our framework, DO3D is a new motion disentanglement module that learns to predict camera ego-motion and instance-aware 3D object motion separately. To alleviate the difficulties in estimating non-rigid 3D object motions, they are decomposed to object-wise 6-DoF global transformations and a pixel-wise local 3D motion deformation field. Qualitative and quantitative experiments are conducted on three benchmark datasets, including KITTI, Cityscapes, and VKITTI2, where our model delivers superior performance in all evaluated settings. For the depth estimation task, our model outperforms all compared research works in the high-resolution setting, attaining an absolute relative depth error (abs rel) of 0.099 on the KITTI benchmark. Besides, our optical flow estimation results (an overall EPE of 7.09 on KITTI) also surpass state-of-the-art methods and largely improve the estimation of dynamic regions, demonstrating the effectiveness of our motion model. Our code will be available.	24 pa... 24 pages, 14 figures, Tech Report	None
Improved LiDAR Odometry and Mapping using Deep Semantic Segmentation and Novel Outliers Detection	2024-03-05	Show Perception is a key element for enabling intelligent autonomous navigation. Understanding the semantics of the surrounding environment and accurate vehicle pose estimation are essential capabilities for autonomous vehicles, including self-driving cars and mobile robots that perform complex tasks. Fast moving platforms like self-driving cars impose a hard challenge for localization and mapping algorithms. In this work, we propose a novel framework for real-time LiDAR odometry and mapping based on LOAM architecture for fast moving platforms. Our framework utilizes semantic information produced by a deep learning model to improve point-to-line and point-to-plane matching between LiDAR scans and build a semantic map of the environment, leading to more accurate motion estimation using LiDAR data. We observe that including semantic information in the matching process introduces a new type of outlier matches to the process, where matching occur between different objects of the same semantic class. To this end, we propose a novel algorithm that explicitly identifies and discards potential outliers in the matching process. In our experiments, we study the effect of improving the matching process on the robustness of LiDAR odometry against high speed motion. Our experimental evaluations on KITTI dataset demonstrate that utilizing semantic information and rejecting outliers significantly enhance the robustness of LiDAR odometry and mapping when there are large gaps between scan acquisition poses, which is typical for fast moving platforms.		None
Explicit Motion Handling and Interactive Prompting for Video Camouflaged Object Detection	2024-03-04	Show Camouflage poses challenges in distinguishing a static target, whereas any movement of the target can break this disguise. Existing video camouflaged object detection (VCOD) approaches take noisy motion estimation as input or model motion implicitly, restricting detection performance in complex dynamic scenes. In this paper, we propose a novel Explicit Motion handling and Interactive Prompting framework for VCOD, dubbed EMIP, which handles motion cues explicitly using a frozen pre-trained optical flow fundamental model. EMIP is characterized by a two-stream architecture for simultaneously conducting camouflaged segmentation and optical flow estimation. Interactions across the dual streams are realized in an interactive prompting way that is inspired by emerging visual prompt learning. Two learnable modules, i.e. the camouflaged feeder and motion collector, are designed to incorporate segmentation-to-motion and motion-to-segmentation prompts, respectively, and enhance outputs of the both streams. The prompt fed to the motion stream is learned by supervising optical flow in a self-supervised manner. Furthermore, we show that long-term historical information can also be incorporated as a prompt into EMIP and achieve more robust results with temporal consistency. Experimental results demonstrate that our EMIP achieves new state-of-the-art records on popular VCOD benchmarks. The code will be publicly available.	9 pages, 6 figures	None
Kick Back & Relax++: Scaling Beyond Ground-Truth Depth with SlowTV & CribsTV	2024-03-03	Show Self-supervised learning is the key to unlocking generic computer vision systems. By eliminating the reliance on ground-truth annotations, it allows scaling to much larger data quantities. Unfortunately, self-supervised monocular depth estimation (SS-MDE) has been limited by the absence of diverse training data. Existing datasets have focused exclusively on urban driving in densely populated cities, resulting in models that fail to generalize beyond this domain. To address these limitations, this paper proposes two novel datasets: SlowTV and CribsTV. These are large-scale datasets curated from publicly available YouTube videos, containing a total of 2M training frames. They offer an incredibly diverse set of environments, ranging from snowy forests to coastal roads, luxury mansions and even underwater coral reefs. We leverage these datasets to tackle the challenging task of zero-shot generalization, outperforming every existing SS-MDE approach and even some state-of-the-art supervised methods. The generalization capabilities of our models are further enhanced by a range of components and contributions: 1) learning the camera intrinsics, 2) a stronger augmentation regime targeting aspect ratio changes, 3) support frame randomization, 4) flexible motion estimation, 5) a modern transformer-based architecture. We demonstrate the effectiveness of each component in extensive ablation experiments. To facilitate the development of future research, we make the datasets, code and pretrained models available to the public at https://github.com/jspenmar/slowtv_monodepth.		Code Link
Consistent and Asymptotically Statistically-Efficient Solution to Camera Motion Estimation	2024-03-02	Show Given 2D point correspondences between an image pair, inferring the camera motion is a fundamental issue in the computer vision community. The existing works generally set out from the epipolar constraint and estimate the essential matrix, which is not optimal in the maximum likelihood (ML) sense. In this paper, we dive into the original measurement model with respect to the rotation matrix and normalized translation vector and formulate the ML problem. We then propose a two-step algorithm to solve it: In the first step, we estimate the variance of measurement noises and devise a consistent estimator based on bias elimination; In the second step, we execute a one-step Gauss-Newton iteration on manifold to refine the consistent estimate. We prove that the proposed estimate owns the same asymptotic statistical properties as the ML estimate: The first is consistency, i.e., the estimate converges to the ground truth as the point number increases; The second is asymptotic efficiency, i.e., the mean squared error of the estimate converges to the theoretical lower bound -- Cramer-Rao bound. In addition, we show that our algorithm has linear time complexity. These appealing characteristics endow our estimator with a great advantage in the case of dense point correspondences. Experiments on both synthetic data and real images demonstrate that when the point number reaches the order of hundreds, our estimator outperforms the state-of-the-art ones in terms of estimation accuracy and CPU time.		None
Fully Convolutional Slice-to-Volume Reconstruction for Single-Stack MRI	2024-02-28	Show In magnetic resonance imaging (MRI), slice-to-volume reconstruction (SVR) refers to computational reconstruction of an unknown 3D magnetic resonance volume from stacks of 2D slices corrupted by motion. While promising, current SVR methods require multiple slice stacks for accurate 3D reconstruction, leading to long scans and limiting their use in time-sensitive applications such as fetal fMRI. Here, we propose a SVR method that overcomes the shortcomings of previous work and produces state-of-the-art reconstructions in the presence of extreme inter-slice motion. Inspired by the recent success of single-view depth estimation methods, we formulate SVR as a single-stack motion estimation task and train a fully convolutional network to predict a motion stack for a given slice stack, producing a 3D reconstruction as a byproduct of the predicted motion. Extensive experiments on the SVR of adult and fetal brains demonstrate that our fully convolutional method is twice as accurate as previous SVR methods. Our code is available at github.com/seannz/svr.	Accep... Accepted to CVPR 2024	None
USB-NeRF: Unrolling Shutter Bundle Adjusted Neural Radiance Fields	2024-02-26	Show Neural Radiance Fields (NeRF) has received much attention recently due to its impressive capability to represent 3D scene and synthesize novel view images. Existing works usually assume that the input images are captured by a global shutter camera. Thus, rolling shutter (RS) images cannot be trivially applied to an off-the-shelf NeRF algorithm for novel view synthesis. Rolling shutter effect would also affect the accuracy of the camera pose estimation (e.g. via COLMAP), which further prevents the success of NeRF algorithm with RS images. In this paper, we propose Unrolling Shutter Bundle Adjusted Neural Radiance Fields (USB-NeRF). USB-NeRF is able to correct rolling shutter distortions and recover accurate camera motion trajectory simultaneously under the framework of NeRF, by modeling the physical image formation process of a RS camera. Experimental results demonstrate that USB-NeRF achieves better performance compared to prior works, in terms of RS effect removal, novel view image synthesis as well as camera motion estimation. Furthermore, our algorithm can also be used to recover high-fidelity high frame-rate global shutter video from a sequence of RS images.		None
A Framework for Fluid Motion Estimation using a Constraint-Based Refinement Approach	2024-02-21	Show Physics-based optical flow models have been successful in capturing the deformities in fluid motion arising from digital imagery. However, a common theoretical framework analyzing several physics-based models is missing. In this regard, we formulate a general framework for fluid motion estimation using a constraint-based refinement approach. We demonstrate that for a particular choice of constraint, our results closely approximate the classical continuity equation-based method for fluid flow. This closeness is theoretically justified by augmented Lagrangian method in a novel way. The convergence of Uzawa iterates is shown using a modified bounded constraint algorithm. The mathematical wellposedness is studied in a Hilbert space setting. Further, we observe a surprising connection to the Cauchy-Riemann operator that diagonalizes the system leading to a diffusive phenomenon involving the divergence and the curl of the flow. Several numerical experiments are performed and the results are shown on different datasets. Additionally, we demonstrate that a flow-driven refinement process involving the curl of the flow outperforms the classical physics-based optical flow method without any additional assumptions on the image data.		None
Refining Pre-Trained Motion Models	2024-02-17	Show Given the difficulty of manually annotating motion in video, the current best motion estimation methods are trained with synthetic data, and therefore struggle somewhat due to a train/test gap. Self-supervised methods hold the promise of training directly on real video, but typically perform worse. These include methods trained with warp error (i.e., color constancy) combined with smoothness terms, and methods that encourage cycle-consistency in the estimates (i.e., tracking backwards should yield the opposite trajectory as tracking forwards). In this work, we take on the challenge of improving state-of-the-art supervised models with self-supervised training. We find that when the initialization is supervised weights, most existing self-supervision techniques actually make performance worse instead of better, which suggests that the benefit of seeing the new data is overshadowed by the noise in the training signal. Focusing on obtaining a "clean" training signal from real-world unlabelled video, we propose to separate label-making and training into two distinct stages. In the first stage, we use the pre-trained model to estimate motion in a video, and then select the subset of motion estimates which we can verify with cycle-consistency. This produces a sparse but accurate pseudo-labelling of the video. In the second stage, we fine-tune the model to reproduce these outputs, while also applying augmentations on the input. We complement this boot-strapping method with simple techniques that densify and re-balance the pseudo-labels, ensuring that we do not merely train on "easy" tracks. We show that our method yields reliable gains over fully-supervised methods in real videos, for both short-term (flow-based) and long-range (multi-frame) pixel tracking.	Accep... Accepted at ICRA 2024	None
TAI-GAN: A Temporally and Anatomically Informed Generative Adversarial Network for early-to-late frame conversion in dynamic cardiac PET inter-frame motion correction	2024-02-14	Show Inter-frame motion in dynamic cardiac positron emission tomography (PET) using rubidium-82 (82-Rb) myocardial perfusion imaging impacts myocardial blood flow (MBF) quantification and the diagnosis accuracy of coronary artery diseases. However, the high cross-frame distribution variation due to rapid tracer kinetics poses a considerable challenge for inter-frame motion correction, especially for early frames where intensity-based image registration techniques often fail. To address this issue, we propose a novel method called Temporally and Anatomically Informed Generative Adversarial Network (TAI-GAN) that utilizes an all-to-one mapping to convert early frames into those with tracer distribution similar to the last reference frame. The TAI-GAN consists of a feature-wise linear modulation layer that encodes channel-wise parameters generated from temporal information and rough cardiac segmentation masks with local shifts that serve as anatomical information. Our proposed method was evaluated on a clinical 82-Rb PET dataset, and the results show that our TAI-GAN can produce converted early frames with high image quality, comparable to the real reference frames. After TAI-GAN conversion, the motion estimation accuracy and subsequent myocardial blood flow (MBF) quantification with both conventional and deep learning-based motion correction methods were improved compared to using the original frames.	Under... Under revision at Medical Image Analysis	None
Tightly Coupled Range Inertial Localization on a 3D Prior Map Based on Sliding Window Factor Graph Optimization	2024-02-08	Show This paper presents a range inertial localization algorithm for a 3D prior map. The proposed algorithm tightly couples scan-to-scan and scan-to-map point cloud registration factors along with IMU factors on a sliding window factor graph. The tight coupling of the scan-to-scan and scan-to-map registration factors enables a smooth fusion of sensor ego-motion estimation and map-based trajectory correction that results in robust tracking of the sensor pose under severe point cloud degeneration and defective regions in a map. We also propose an initial sensor state estimation algorithm that robustly estimates the gravity direction and IMU state and helps perform global localization in 3- or 4-DoF for system initialization without prior position information. Experimental results show that the proposed method outperforms existing state-of-the-art methods in extremely severe situations where the point cloud data becomes degenerate, there are momentary sensor interruptions, or the sensor moves along the map boundary or into unmapped regions.	IEEE ... IEEE International Conference on Robotics and Automation (ICRA2024)	None
MIRT: a simultaneous reconstruction and affine motion compensation technique for four dimensional computed tomography (4DCT)	2024-02-07	Show In four-dimensional computed tomography (4DCT), 3D images of moving or deforming samples are reconstructed from a set of 2D projection images. Recent techniques for iterative motion-compensated reconstruction either necessitate a reference acquisition or alternate image reconstruction and motion estimation steps. In these methods, the motion estimation step involves the estimation of either complete deformation vector fields (DVFs) or a limited set of parameters corresponding to the affine motion, including rigid motion or scaling. The majority of these approaches rely on nested iterations, incurring significant computational expenses. Notably, despite the direct benefits of an analytical formulation and a substantial reduction in computational complexity, there has been no exploration into parameterizing DVFs for general affine motion in CT imaging. In this work, we propose the Motion-compensated Iterative Reconstruction Technique (MIRT)- an efficient iterative reconstruction scheme that combines image reconstruction and affine motion estimation in a single update step, based on the analytical gradients of the motion towards both the reconstruction and the affine motion parameters. When most of the state-of-the-art 4DCT methods have not attempted to be tested on real data, results from simulation and real experiments show that our method outperforms the state-of-the-art CT reconstruction with affine motion correction methods in computational feasibility and projection distance. In particular, this allows accurate reconstruction for a proper microscale diamond in the appearance of motion from the practically acquired projection radiographs, which leads to a novel application of 4DCT.	Submi... Submitted to the SIAM Journal on Imaging Sciences (SIIMS)	None
WS-SfMLearner: Self-supervised Monocular Depth and Ego-motion Estimation on Surgical Videos with Unknown Camera Parameters	2024-02-06	Show Depth estimation in surgical video plays a crucial role in many image-guided surgery procedures. However, it is difficult and time consuming to create depth map ground truth datasets in surgical videos due in part to inconsistent brightness and noise in the surgical scene. Therefore, building an accurate and robust self-supervised depth and camera ego-motion estimation system is gaining more attention from the computer vision community. Although several self-supervision methods alleviate the need for ground truth depth maps and poses, they still need known camera intrinsic parameters, which are often missing or not recorded. Moreover, the camera intrinsic prediction methods in existing works depend heavily on the quality of datasets. In this work, we aimed to build a self-supervised depth and ego-motion estimation system which can predict not only accurate depth maps and camera pose, but also camera intrinsic parameters. We proposed a cost-volume-based supervision manner to give the system auxiliary supervision for camera parameters prediction. The experimental results showed that the proposed method improved the accuracy of estimated camera parameters, ego-motion, and depth estimation.	Accep... Accepted by SPIE 2024	None
Video Semantic Communication with Major Object Extraction and Contextual Video Encoding	2024-02-02	Show This paper studies an end-to-end video semantic communication system for massive communication. In the considered system, the transmitter must continuously send the video to the receiver to facilitate character reconstruction in immersive applications, such as interactive video conference. However, transmitting the original video information with substantial amounts of data poses a challenge to the limited wireless resources. To address this issue, we reduce the amount of data transmitted by making the transmitter extract and send the semantic information from the video, which refines the major object and the correlation of time and space in the video. Specifically, we first develop a video semantic communication system based on major object extraction (MOE) and contextual video encoding (CVE) to achieve efficient video transmission. Then, we design the MOE and CVE modules with convolutional neural network based motion estimation, contextual extraction and entropy coding. Simulation results show that compared to the traditional coding schemes, the proposed method can reduce the amount of transmitted data by up to 25% while increasing the peak signal-to-noise ratio (PSNR) of the reconstructed video by up to 14%.	6 pag... 6 pages, 9 figures, accepted by IEEE WCNC wksp 2024	None
Motion Guidance: Diffusion-Based Image Editing with Differentiable Motion Estimators	2024-01-31	Show Diffusion models are capable of generating impressive images conditioned on text descriptions, and extensions of these models allow users to edit images at a relatively coarse scale. However, the ability to precisely edit the layout, position, pose, and shape of objects in images with diffusion models is still difficult. To this end, we propose motion guidance, a zero-shot technique that allows a user to specify dense, complex motion fields that indicate where each pixel in an image should move. Motion guidance works by steering the diffusion sampling process with the gradients through an off-the-shelf optical flow network. Specifically, we design a guidance loss that encourages the sample to have the desired motion, as estimated by a flow network, while also being visually similar to the source image. By simultaneously sampling from a diffusion model and guiding the sample to have low guidance loss, we can obtain a motion-edited image. We demonstrate that our technique works on complex motions and produces high quality edits of real and generated images.		None
Is Registering Raw Tagged-MR Enough for Strain Estimation in the Era of Deep Learning?	2024-01-31	Show Magnetic Resonance Imaging with tagging (tMRI) has long been utilized for quantifying tissue motion and strain during deformation. However, a phenomenon known as tag fading, a gradual decrease in tag visibility over time, often complicates post-processing. The first contribution of this study is to model tag fading by considering the interplay between $T_1$ relaxation and the repeated application of radio frequency (RF) pulses during serial imaging sequences. This is a factor that has been overlooked in prior research on tMRI post-processing. Further, we have observed an emerging trend of utilizing raw tagged MRI within a deep learning-based (DL) registration framework for motion estimation. In this work, we evaluate and analyze the impact of commonly used image similarity objectives in training DL registrations on raw tMRI. This is then compared with the Harmonic Phase-based approach, a traditional approach which is claimed to be robust to tag fading. Our findings, derived from both simulated images and an actual phantom scan, reveal the limitations of various similarity losses in raw tMRI and emphasize caution in registration tasks where image intensity changes over time.	Accep... Accepted to SPIE Medical Imaging 2024 (oral)	None
Spatial Decomposition and Temporal Fusion based Inter Prediction for Learned Video Compression	2024-01-29	Show Video compression performance is closely related to the accuracy of inter prediction. It tends to be difficult to obtain accurate inter prediction for the local video regions with inconsistent motion and occlusion. Traditional video coding standards propose various technologies to handle motion inconsistency and occlusion, such as recursive partitions, geometric partitions, and long-term references. However, existing learned video compression schemes focus on obtaining an overall minimized prediction error averaged over all regions while ignoring the motion inconsistency and occlusion in local regions. In this paper, we propose a spatial decomposition and temporal fusion based inter prediction for learned video compression. To handle motion inconsistency, we propose to decompose the video into structure and detail (SDD) components first. Then we perform SDD-based motion estimation and SDD-based temporal context mining for the structure and detail components to generate short-term temporal contexts. To handle occlusion, we propose to propagate long-term temporal contexts by recurrently accumulating the temporal information of each historical reference feature and fuse them with short-term temporal contexts. With the SDD-based motion model and long short-term temporal contexts fusion, our proposed learned video codec can obtain more accurate inter prediction. Comprehensive experimental results demonstrate that our codec outperforms the reference software of H.266/VVC on all common test datasets for both PSNR and MS-SSIM.		None
Conditional Neural Video Coding with Spatial-Temporal Super-Resolution	2024-01-25	Show This document is an expanded version of a one-page abstract originally presented at the 2024 Data Compression Conference. It describes our proposed method for the video track of the Challenge on Learned Image Compression (CLIC) 2024. Our scheme follows the typical hybrid coding framework with some novel techniques. Firstly, we adopt Spynet network to produce accurate motion vectors for motion estimation. Secondly, we introduce the context mining scheme with conditional frame coding to fully exploit the spatial-temporal information. As for the low target bitrates given by CLIC, we integrate spatial-temporal super-resolution modules to improve rate-distortion performance. Our team name is IMCLVC.	Accep... Accepted by the 2024 Data Compression Conference (DCC) for presentation as a poster	None
Event-Based Visual Odometry on Non-Holonomic Ground Vehicles	2024-01-17	Show Despite the promise of superior performance under challenging conditions, event-based motion estimation remains a hard problem owing to the difficulty of extracting and tracking stable features from event streams. In order to robustify the estimation, it is generally believed that fusion with other sensors is a requirement. In this work, we demonstrate reliable, purely event-based visual odometry on planar ground vehicles by employing the constrained non-holonomic motion model of Ackermann steering platforms. We extend single feature n-linearities for regular frame-based cameras to the case of quasi time-continuous event-tracks, and achieve a polynomial form via variable degree Taylor expansions. Robust averaging over multiple event tracks is simply achieved via histogram voting. As demonstrated on both simulated and real data, our algorithm achieves accurate and robust estimates of the vehicle's instantaneous rotational velocity, and thus results that are comparable to the delta rotations obtained by frame-based sensors under normal conditions. We furthermore significantly outperform the more traditional alternatives in challenging illumination scenarios. The code is available at \url{https://github.com/gowanting/NHEVO}.	Accepted by 3DV 2024	Code Link
Plug-in for visualizing 3D tool tracking from videos of Minimally Invasive Surgeries	2024-01-12	Show This paper tackles instrument tracking and 3D visualization challenges in minimally invasive surgery (MIS), crucial for computer-assisted interventions. Conventional and robot-assisted MIS encounter issues with limited 2D camera projections and minimal hardware integration. The objective is to track and visualize the entire surgical instrument, including shaft and metallic clasper, enabling safe navigation within the surgical environment. The proposed method involves 2D tracking based on segmentation maps, facilitating creation of labeled dataset without extensive ground-truth knowledge. Geometric changes in 2D intervals express motion, and kinematics based algorithms process results into 3D tracking information. Synthesized and experimental results in 2D and 3D motion estimates demonstrate negligible errors, validating the method for labeling and motion tracking of instruments in MIS videos. The conclusion underscores the proposed 2D segmentation technique's simplicity and computational efficiency, emphasizing its potential as direct plug-in for 3D visualization in instrument tracking and MIS practices.		None
Estimating continuous data of wrist joint angles using ultrasound images	2024-01-04	Show Ultrasound imaging has recently been introduced as a sensing interface for joint motion estimation. The use of ultrasound images as an estimation method is expected to improve the control performance of assistive devices and human--machine interfaces. This study aimed to estimate continuous wrist joint angles using ultrasound images. Specifically, in an experiment, joint angle information was obtained during extension--flexion movements, and ultrasound images of the associated muscles were acquired. Using the features obtained from ultrasound images, a multivariate linear regression model was used to estimate the joint angles. The coordinates of the feature points obtained using optical flow from the ultrasound images were used as explanatory variables of the multivariate linear regression model. The model was trained and tested for each trial by each participant to verify the estimation accuracy. The results show that the mean and standard deviation of the estimation accuracy for all trials were root mean square error (RMSE)=1.82 $\pm$ 0.54 deg and coefficient of determination (R2)=0.985 $\pm$ 0.009. Our method achieves a highly accurate estimation of joint angles compared with previous studies using other signals, such as surface electromyography, while the multivariate linear regression model is simple and both computational and model training costs are low.		None
HMP: Hand Motion Priors for Pose and Shape Estimation from Video	2023-12-27	Show Understanding how humans interact with the world necessitates accurate 3D hand pose estimation, a task complicated by the hand's high degree of articulation, frequent occlusions, self-occlusions, and rapid motions. While most existing methods rely on single-image inputs, videos have useful cues to address aforementioned issues. However, existing video-based 3D hand datasets are insufficient for training feedforward models to generalize to in-the-wild scenarios. On the other hand, we have access to large human motion capture datasets which also include hand motions, e.g. AMASS. Therefore, we develop a generative motion prior specific for hands, trained on the AMASS dataset which features diverse and high-quality hand motions. This motion prior is then employed for video-based 3D hand motion estimation following a latent optimization approach. Our integration of a robust motion prior significantly enhances performance, especially in occluded scenarios. It produces stable, temporally consistent results that surpass conventional single-frame methods. We demonstrate our method's efficacy via qualitative and quantitative evaluations on the HO3D and DexYCB datasets, with special emphasis on an occlusion-focused subset of HO3D. Code is available at https://hmp.is.tue.mpg.de		None
Video Frame Interpolation with Region-Distinguishable Priors from SAM	2023-12-26	Show In existing Video Frame Interpolation (VFI) approaches, the motion estimation between neighboring frames plays a crucial role. However, the estimation accuracy in existing methods remains a challenge, primarily due to the inherent ambiguity in identifying corresponding areas in adjacent frames for interpolation. Therefore, enhancing accuracy by distinguishing different regions before motion estimation is of utmost importance. In this paper, we introduce a novel solution involving the utilization of open-world segmentation models, e.g., SAM (Segment Anything Model), to derive Region-Distinguishable Priors (RDPs) in different frames. These RDPs are represented as spatial-varying Gaussian mixtures, distinguishing an arbitrary number of areas with a unified modality. RDPs can be integrated into existing motion-based VFI methods to enhance features for motion estimation, facilitated by our designed play-and-plug Hierarchical Region-aware Feature Fusion Module (HRFFM). HRFFM incorporates RDP into various hierarchical stages of VFI's encoder, using RDP-guided Feature Normalization (RDPFN) in a residual learning manner. With HRFFM and RDP, the features within VFI's encoder exhibit similar representations for matched regions in neighboring frames, thus improving the synthesis of intermediate frames. Extensive experiments demonstrate that HRFFM consistently enhances VFI performance across various scenes.	Code ... Code will be released	None
SAMFlow: Eliminating Any Fragmentation in Optical Flow with Segment Anything Model	2023-12-21	Show Optical Flow Estimation aims to find the 2D dense motion field between two frames. Due to the limitation of model structures and training datasets, existing methods often rely too much on local clues and ignore the integrity of objects, resulting in fragmented motion estimation. Through theoretical analysis, we find the pre-trained large vision models are helpful in optical flow estimation, and we notice that the recently famous Segment Anything Model (SAM) demonstrates a strong ability to segment complete objects, which is suitable for solving the fragmentation problem. We thus propose a solution to embed the frozen SAM image encoder into FlowFormer to enhance object perception. To address the challenge of in-depth utilizing SAM in non-segmentation tasks like optical flow estimation, we propose an Optical Flow Task-Specific Adaption scheme, including a Context Fusion Module to fuse the SAM encoder with the optical flow context encoder, and a Context Adaption Module to adapt the SAM features for optical flow task with Learned Task-Specific Embedding. Our proposed SAMFlow model reaches 0.86/2.10 clean/final EPE and 3.55/12.32 EPE/F1-all on Sintel and KITTI-15 training set, surpassing Flowformer by 8.5%/9.9% and 13.2%/16.3%. Furthermore, our model achieves state-of-the-art performance on the Sintel and KITTI-15 benchmarks, ranking #1 among all two-frame methods on Sintel clean pass.	Accep... Accepted by AAAI 2024	None
Loss it right: Euclidean and Riemannian Metrics in Learning-based Visual Odometry	2023-12-19	Show This paper overviews different pose representations and metric functions in visual odometry (VO) networks. The performance of VO networks heavily relies on how their architecture encodes the information. The choice of pose representation and loss function significantly impacts network convergence and generalization. We investigate these factors in the VO network DeepVO by implementing loss functions based on Euler, quaternion, and chordal distance and analyzing their influence on performance. The results of this study provide insights into how loss functions affect the designing of efficient and accurate VO networks for camera motion estimation. The experiments illustrate that a distance that complies with the mathematical requirements of a metric, such as the chordal distance, provides better generalization and faster convergence. The code for the experiments can be found at https://github.com/remaro-network/Loss_VO_right		Code Link
Improving Audio-Visual Segmentation with Bidirectional Generation	2023-12-19	Show The aim of audio-visual segmentation (AVS) is to precisely differentiate audible objects within videos down to the pixel level. Traditional approaches often tackle this challenge by combining information from various modalities, where the contribution of each modality is implicitly or explicitly modeled. Nevertheless, the interconnections between different modalities tend to be overlooked in audio-visual modeling. In this paper, inspired by the human ability to mentally simulate the sound of an object and its visual appearance, we introduce a bidirectional generation framework. This framework establishes robust correlations between an object's visual characteristics and its associated sound, thereby enhancing the performance of AVS. To achieve this, we employ a visual-to-audio projection component that reconstructs audio features from object segmentation masks and minimizes reconstruction errors. Moreover, recognizing that many sounds are linked to object movements, we introduce an implicit volumetric motion estimation module to handle temporal dynamics that may be challenging to capture using conventional optical flow methods. To showcase the effectiveness of our approach, we conduct comprehensive experiments and analyses on the widely recognized AVSBench benchmark. As a result, we establish a new state-of-the-art performance level in the AVS benchmark, particularly excelling in the challenging MS3 subset which involves segmenting multiple sound sources. To facilitate reproducibility, we plan to release both the source code and the pre-trained model.	AAAI ... AAAI Camera Ready. Dawei Hao and Yuxin Mao contribute equality to this paper. Yiran Zhong is the corresponding author. The code will be released at https://github.com/OpenNLPLab/AVS-bidirectional	Code Link
Egocentric Whole-Body Motion Capture with FisheyeViT and Diffusion-Based Motion Refinement	2023-12-02	Show In this work, we explore egocentric whole-body motion capture using a single fisheye camera, which simultaneously estimates human body and hand motion. This task presents significant challenges due to three factors: the lack of high-quality datasets, fisheye camera distortion, and human body self-occlusion. To address these challenges, we propose a novel approach that leverages FisheyeViT to extract fisheye image features, which are subsequently converted into pixel-aligned 3D heatmap representations for 3D human body pose prediction. For hand tracking, we incorporate dedicated hand detection and hand pose estimation networks for regressing 3D hand poses. Finally, we develop a diffusion-based whole-body motion prior model to refine the estimated whole-body motion while accounting for joint uncertainties. To train these networks, we collect a large synthetic dataset, EgoWholeBody, comprising 840,000 high-quality egocentric images captured across a diverse range of whole-body motion sequences. Quantitative and qualitative evaluations demonstrate the effectiveness of our method in producing high-quality whole-body motion estimates from a single egocentric camera.		None
Self-Supervised Motion Magnification by Backpropagating Through Optical Flow	2023-11-28	Show This paper presents a simple, self-supervised method for magnifying subtle motions in video: given an input video and a magnification factor, we manipulate the video such that its new optical flow is scaled by the desired amount. To train our model, we propose a loss function that estimates the optical flow of the generated video and penalizes how far if deviates from the given magnification factor. Thus, training involves differentiating through a pretrained optical flow network. Since our model is self-supervised, we can further improve its performance through test-time adaptation, by finetuning it on the input video. It can also be easily extended to magnify the motions of only user-selected objects. Our approach avoids the need for synthetic magnification datasets that have been used to train prior learning-based approaches. Instead, it leverages the existing capabilities of off-the-shelf motion estimators. We demonstrate the effectiveness of our method through evaluations of both visual quality and quantitative metrics on a range of real-world and synthetic videos, and we show our method works for both supervised and unsupervised optical flow methods.		None
MCPNS: A Macropixel Collocated Position and Its Neighbors Search for Plenoptic 2.0 Video Coding	2023-11-28	Show Recently, it was demonstrated that a newly focused plenoptic 2.0 camera can capture much higher spatial resolution owing to its effective light field sampling, as compared to a traditional unfocused plenoptic 1.0 camera. However, due to the nature difference of the optical structure between the plenoptic 1.0 and 2.0 cameras, the existing fast motion estimation (ME) method for plenoptic 1.0 videos is expected to be sub-optimal for encoding plenoptic 2.0 videos. In this paper, we point out the main motion characteristic differences between plenoptic 1.0 and 2.0 videos and then propose a new fast ME, called macropixel collocated position and its neighbors search (MCPNS) for plenoptic 2.0 videos. In detail, we propose to reduce the number of macropixel collocated position (MCP) search candidates based on the new observation of center-biased motion vector distribution at macropixel resolution. After that, due to large motion deviation behavior around each MCP location in plenoptic 2.0 videos, we propose to select a certain number of key MCP locations with the lowest matching cost to perform the neighbors MCP search to improve the motion search accuracy. Different from existing methods, our method can achieve better performance without requiring prior knowledge of microlens array orientations. Our simulation results confirmed the effectiveness of the proposed algorithm in terms of both bitrate savings and computational costs compared to existing methods.	Under review	None
MaskFlow: Object-Aware Motion Estimation	2023-11-21	Show We introduce a novel motion estimation method, MaskFlow, that is capable of estimating accurate motion fields, even in very challenging cases with small objects, large displacements and drastic appearance changes. In addition to lower-level features, that are used in other Deep Neural Network (DNN)-based motion estimation methods, MaskFlow draws from object-level features and segmentations. These features and segmentations are used to approximate the objects' translation motion field. We propose a novel and effective way of incorporating the incomplete translation motion field into a subsequent motion estimation network for refinement and completion. We also produced a new challenging synthetic dataset with motion field ground truth, and also provide extra ground truth for the object-instance matchings and corresponding segmentation masks. We demonstrate that MaskFlow outperforms state of the art methods when evaluated on our new challenging dataset, whilst still producing comparable results on the popular FlyingThings3D benchmark dataset.		None
Enhanced Spatio-Temporal Context for Temporally Consistent Robust 3D Human Motion Recovery from Monocular Videos	2023-11-20	Show Recovering temporally consistent 3D human body pose, shape and motion from a monocular video is a challenging task due to (self-)occlusions, poor lighting conditions, complex articulated body poses, depth ambiguity, and limited availability of annotated data. Further, doing a simple perframe estimation is insufficient as it leads to jittery and implausible results. In this paper, we propose a novel method for temporally consistent motion estimation from a monocular video. Instead of using generic ResNet-like features, our method uses a body-aware feature representation and an independent per-frame pose and camera initialization over a temporal window followed by a novel spatio-temporal feature aggregation by using a combination of self-similarity and self-attention over the body-aware features and the perframe initialization. Together, they yield enhanced spatiotemporal context for every frame by considering remaining past and future frames. These features are used to predict the pose and shape parameters of the human body model, which are further refined using an LSTM. Experimental results on the publicly available benchmark data show that our method attains significantly lower acceleration error and outperforms the existing state-of-the-art methods over all key quantitative evaluation metrics, including complex scenarios like partial occlusion, complex poses and even relatively low illumination.		None
Differential Motion Evolution for Fine-Grained Motion Deformation in Unsupervised Image Animation	2023-11-19	Show Image animation is the task of transferring the motion of a driving video to a given object in a source image. While great progress has recently been made in unsupervised motion transfer, requiring no labeled data or domain priors, many current unsupervised approaches still struggle to capture the motion deformations when large motion/view discrepancies occur between the source and driving domains. Under such conditions, there is simply not enough information to capture the motion field properly. We introduce DiME (Differential Motion Evolution), an end-to-end unsupervised motion transfer framework integrating differential refinement for motion estimation. Key findings are twofold: (1) by capturing the motion transfer with an ordinary differential equation (ODE), it helps to regularize the motion field, and (2) by utilizing the source image itself, we are able to inpaint occluded/missing regions arising from large motion changes. Additionally, we also propose a natural extension to the ODE idea, which is that DiME can easily leverage multiple different views of the source object whenever they are available by modeling an ODE per view. Extensive experiments across 9 benchmarks show DiME outperforms the state-of-the-arts by a significant margin and generalizes much better to unseen objects.		None
A Video-Based Activity Classification of Human Pickers in Agriculture	2023-11-17	Show In farming systems, harvesting operations are tedious, time- and resource-consuming tasks. Based on this, deploying a fleet of autonomous robots to work alongside farmworkers may provide vast productivity and logistics benefits. Then, an intelligent robotic system should monitor human behavior, identify the ongoing activities and anticipate the worker's needs. In this work, the main contribution consists of creating a benchmark model for video-based human pickers detection, classifying their activities to serve in harvesting operations for different agricultural scenarios. Our solution uses the combination of a Mask Region-based Convolutional Neural Network (Mask R-CNN) for object detection and optical flow for motion estimation with newly added statistical attributes of flow motion descriptors, named as Correlation Sensitivity (CS). A classification criterion is defined based on the Kernel Density Estimation (KDE) analysis and K-means clustering algorithm, which are implemented upon in-house collected dataset from different crop fields like strawberry polytunnels and apple tree orchards. The proposed framework is quantitatively analyzed using sensitivity, specificity, and accuracy measures and shows satisfactory results amidst various dataset challenges such as lighting variation, blur, and occlusions.	4 pag... 4 pages, 6 figures, 3 tables	None
Dense Visual Odometry Using Genetic Algorithm	2023-11-10	Show Our work aims to estimate the camera motion mounted on the head of a mobile robot or a moving object from RGB-D images in a static scene. The problem of motion estimation is transformed into a nonlinear least squares function. Methods for solving such problems are iterative. Various classic methods gave an iterative solution by linearizing this function. We can also use the metaheuristic optimization method to solve this problem and improve results. In this paper, a new algorithm is developed for visual odometry using a sequence of RGB-D images. This algorithm is based on a genetic algorithm. The proposed iterative genetic algorithm searches using particles to estimate the optimal motion and then compares it to the traditional methods. To evaluate our method, we use the root mean square error to compare it with the based energy method and another metaheuristic method. We prove the efficiency of our innovative algorithm on a large set of images.	9 pages, 9 figures	None
Hard to Track Objects with Irregular Motions and Similar Appearances? Make It Easier by Buffering the Matching Space	2023-11-07	Show We propose a Cascaded Buffered IoU (C-BIoU) tracker to track multiple objects that have irregular motions and indistinguishable appearances. When appearance features are unreliable and geometric features are confused by irregular motions, applying conventional Multiple Object Tracking (MOT) methods may generate unsatisfactory results. To address this issue, our C-BIoU tracker adds buffers to expand the matching space of detections and tracks, which mitigates the effect of irregular motions in two aspects: one is to directly match identical but non-overlapping detections and tracks in adjacent frames, and the other is to compensate for the motion estimation bias in the matching space. In addition, to reduce the risk of overexpansion of the matching space, cascaded matching is employed: first matching alive tracks and detections with a small buffer, and then matching unmatched tracks and detections with a large buffer. Despite its simplicity, our C-BIoU tracker works surprisingly well and achieves state-of-the-art results on MOT datasets that focus on irregular motions and indistinguishable appearances. Moreover, the C-BIoU tracker is the dominant component for our 2-nd place solution in the CVPR'22 SoccerNet MOT and ECCV'22 MOTComplex DanceTrack challenges. Finally, we analyze the limitation of our C-BIoU tracker in ablation studies and discuss its application scope.	Accep... Accepted to WACV 2023. arXiv admin note: text overlap with arXiv:2211.13509	None
Task-Oriented Human-Object Interactions Generation with Implicit Neural Representations	2023-11-04	Show Digital human motion synthesis is a vibrant research field with applications in movies, AR/VR, and video games. Whereas methods were proposed to generate natural and realistic human motions, most only focus on modeling humans and largely ignore object movements. Generating task-oriented human-object interaction motions in simulation is challenging. For different intents of using the objects, humans conduct various motions, which requires the human first to approach the objects and then make them move consistently with the human instead of staying still. Also, to deploy in downstream applications, the synthesized motions are desired to be flexible in length, providing options to personalize the predicted motions for various purposes. To this end, we propose TOHO: Task-Oriented Human-Object Interactions Generation with Implicit Neural Representations, which generates full human-object interaction motions to conduct specific tasks, given only the task type, the object, and a starting human status. TOHO generates human-object motions in three steps: 1) it first estimates the keyframe poses of conducting a task given the task type and object information; 2) then, it infills the keyframes and generates continuous motions; 3) finally, it applies a compact closed-form object motion estimation to generate the object motion. Our method generates continuous motions that are parameterized only by the temporal coordinate, which allows for upsampling or downsampling of the sequence to arbitrary frames and adjusting the motion speeds by designing the temporal coordinate vector. We demonstrate the effectiveness of our method, both qualitatively and quantitatively. This work takes a step further toward general human-scene interaction simulation.	To be... To be published in WACV 2024	None
Provably Robust Semi-Infinite Program Under Collision Constraints via Subdivision	2023-11-03	Show We present a semi-infinite program (SIP) solver for trajectory optimizations of general articulated robots. These problems are more challenging than standard Nonlinear Program (NLP) by involving an infinite number of non-convex, collision constraints. Prior SIP solvers based on constraint sampling cannot guarantee the satisfaction of all constraints. Instead, our method uses a conservative bound on articulated body motions to ensure the solution feasibility throughout the optimization procedure. We further use subdivision to adaptively reduce the error in conservative motion estimation. Combined, we prove that our SIP solver guarantees feasibility while approaches the critical point of SIP problems up to arbitrary user-provided precision. We have verified our method on a row of trajectory optimization problems involving industrial robot arms and UAVs, where our method can generate collision-free, locally optimal trajectories within a couple minutes.		None
Joint 3D Shape and Motion Estimation from Rolling Shutter Light-Field Images	2023-11-02	Show In this paper, we propose an approach to address the problem of 3D reconstruction of scenes from a single image captured by a light-field camera equipped with a rolling shutter sensor. Our method leverages the 3D information cues present in the light-field and the motion information provided by the rolling shutter effect. We present a generic model for the imaging process of this sensor and a two-stage algorithm that minimizes the re-projection error while considering the position and motion of the camera in a motion-shape bundle adjustment estimation strategy. Thereby, we provide an instantaneous 3D shape-and-pose-and-velocity sensing paradigm. To the best of our knowledge, this is the first study to leverage this type of sensor for this purpose. We also present a new benchmark dataset composed of different light-fields showing rolling shutter effects, which can be used as a common base to improve the evaluation and tracking the progress in the field. We demonstrate the effectiveness and advantages of our approach through several experiments conducted for different scenes and types of motions. The source code and dataset are publicly available at: https://github.com/ICB-Vision-AI/RSLF		Code Link
VNVC: A Versatile Neural Video Coding Framework for Efficient Human-Machine Vision	2023-11-01	Show Almost all digital videos are coded into compact representations before being transmitted. Such compact representations need to be decoded back to pixels before being displayed to humans and - as usual - before being enhanced/analyzed by machine vision algorithms. Intuitively, it is more efficient to enhance/analyze the coded representations directly without decoding them into pixels. Therefore, we propose a versatile neural video coding (VNVC) framework, which targets learning compact representations to support both reconstruction and direct enhancement/analysis, thereby being versatile for both human and machine vision. Our VNVC framework has a feature-based compression loop. In the loop, one frame is encoded into compact representations and decoded to an intermediate feature that is obtained before performing reconstruction. The intermediate feature can be used as reference in motion compensation and motion estimation through feature-based temporal context mining and cross-domain motion encoder-decoder to compress the following frames. The intermediate feature is directly fed into video reconstruction, video enhancement, and video analysis networks to evaluate its effectiveness. The evaluation shows that our framework with the intermediate feature achieves high compression efficiency for video reconstruction and satisfactory task performances with lower complexities.		None
Multi-body SE(3) Equivariance for Unsupervised Rigid Segmentation and Motion Estimation	2023-10-31	Show A truly generalizable approach to rigid segmentation and motion estimation is fundamental to 3D understanding of articulated objects and moving scenes. In view of the closely intertwined relationship between segmentation and motion estimates, we present an SE(3) equivariant architecture and a training strategy to tackle this task in an unsupervised manner. Our architecture is composed of two interconnected, lightweight heads. These heads predict segmentation masks using point-level invariant features and estimate motion from SE(3) equivariant features, all without the need for category information. Our training strategy is unified and can be implemented online, which jointly optimizes the predicted segmentation and motion by leveraging the interrelationships among scene flow, segmentation mask, and rigid transformations. We conduct experiments on four datasets to demonstrate the superiority of our method. The results show that our method excels in both model performance and computational efficiency, with only 0.25M parameters and 0.92G FLOPs. To the best of our knowledge, this is the first work designed for category-agnostic part-level SE(3) equivariance in dynamic point clouds.	To ap... To appear at NeurIPS 2023	None
Video Frame Interpolation with Many-to-many Splatting and Spatial Selective Refinement	2023-10-29	Show In this work, we first propose a fully differentiable Many-to-Many (M2M) splatting framework to interpolate frames efficiently. Given a frame pair, we estimate multiple bidirectional flows to directly forward warp the pixels to the desired time step before fusing overlapping pixels. In doing so, each source pixel renders multiple target pixels and each target pixel can be synthesized from a larger area of visual context, establishing a many-to-many splatting scheme with robustness to undesirable artifacts. For each input frame pair, M2M has a minuscule computational overhead when interpolating an arbitrary number of in-between frames, hence achieving fast multi-frame interpolation. However, directly warping and fusing pixels in the intensity domain is sensitive to the quality of motion estimation and may suffer from less effective representation capacity. To improve interpolation accuracy, we further extend an M2M++ framework by introducing a flexible Spatial Selective Refinement (SSR) component, which allows for trading computational efficiency for interpolation quality and vice versa. Instead of refining the entire interpolated frame, SSR only processes difficult regions selected under the guidance of an estimated error map, thereby avoiding redundant computation. Evaluation on multiple benchmark datasets shows that our method is able to improve the efficiency while maintaining competitive video interpolation quality, and it can be adjusted to use more or less compute as needed.	T-PAM... T-PAMI. arXiv admin note: substantial text overlap with arXiv:2204.03513	None
PACE: Human and Camera Motion Estimation from in-the-wild Videos	2023-10-20	Show We present a method to estimate human motion in a global scene from moving cameras. This is a highly challenging task due to the coupling of human and camera motions in the video. To address this problem, we propose a joint optimization framework that disentangles human and camera motions using both foreground human motion priors and background scene features. Unlike existing methods that use SLAM as initialization, we propose to tightly integrate SLAM and human motion priors in an optimization that is inspired by bundle adjustment. Specifically, we optimize human and camera motions to match both the observed human pose and scene features. This design combines the strengths of SLAM and motion priors, which leads to significant improvements in human and camera motion estimation. We additionally introduce a motion prior that is suitable for batch optimization, making our approach significantly more efficient than existing approaches. Finally, we propose a novel synthetic dataset that enables evaluating camera motion in addition to human motion from dynamic videos. Experiments on the synthetic and real-world RICH datasets demonstrate that our approach substantially outperforms prior art in recovering both human and camera motions.	3DV 2... 3DV 2024. Project page: https://nvlabs.github.io/PACE/	Code Link
A mathematical study of joint image reconstruction and motion estimation using optimal control	2023-10-20	Show Spatiotemporal dynamic medical imaging is critical in clinical applications, such as tomographic imaging of the heart or lung. To address such kind of spatiotemporal imaging problems, essentially, a time-dependent dynamic inverse problem, the variational model with intensity, edge feature and topology preservations was proposed for joint image reconstruction and motion estimation in the previous paper [C. Chen, B. Gris, and O. "Oktem, SIAM J. Imaging Sci., 12 (2019), pp. 1686--1719], which is suitable to invert the time-dependent sparse sampling data for the motion target with large diffeomorphic deformations. However, the existence of solution to the model has not been given yet. In order to preserve its topological structure and edge feature of the motion target, the unknown velocity field in the model is restricted into the admissible Hilbert space, and the unknown template image is modeled in the space of bounded variation functions. Under this framework, this paper analyzes and proves the solution existence of its time-discretized version from the point view of optimal control. Specifically, there exists a constraint of transport equation in the equivalent optimal control model. We rigorously demonstrate the closure of the equation, including the solution existence and uniqueness, the stability of the associated nonlinear solution operator, and the convergence. Finally, the solution existence of that model can be concluded.	29 pages	None
Towards Anytime Optical Flow Estimation with Event Cameras	2023-10-19	Show Optical flow estimation is a fundamental task in the field of autonomous driving. Event cameras are capable of responding to log-brightness changes in microseconds. Its characteristic of producing responses only to the changing region is particularly suitable for optical flow estimation. In contrast to the super low-latency response speed of event cameras, existing datasets collected via event cameras, however, only provide limited frame rate optical flow ground truth, (e.g., at 10Hz), greatly restricting the potential of event-driven optical flow. To address this challenge, we put forward a high-frame-rate, low-latency event representation Unified Voxel Grid, sequentially fed into the network bin by bin. We then propose EVA-Flow, an EVent-based Anytime Flow estimation network to produce high-frame-rate event optical flow with only low-frame-rate optical flow ground truth for supervision. The key component of our EVA-Flow is the stacked Spatiotemporal Motion Refinement (SMR) module, which predicts temporally dense optical flow and enhances the accuracy via spatial-temporal motion refinement. The time-dense feature warping utilized in the SMR module provides implicit supervision for the intermediate optical flow. Additionally, we introduce the Rectified Flow Warp Loss (RFWL) for the unsupervised evaluation of intermediate optical flow in the absence of ground truth. This is, to the best of our knowledge, the first work focusing on anytime optical flow estimation via event cameras. A comprehensive variety of experiments on MVSEC, DESC, and our EVA-FlowSet demonstrates that EVA-Flow achieves competitive performance, super-low-latency (5ms), fastest inference (9.2ms), time-dense motion estimation (200Hz), and strong generalization. Our code will be available at https://github.com/Yaozhuwa/EVA-Flow.	Code ... Code will be available at https://github.com/Yaozhuwa/EVA-Flow	Code Link
Multiscale Motion-Aware and Spatial-Temporal-Channel Contextual Coding Network for Learned Video Compression	2023-10-19	Show Recently, learned video compression has achieved exciting performance. Following the traditional hybrid prediction coding framework, most learned methods generally adopt the motion estimation motion compensation (MEMC) method to remove inter-frame redundancy. However, inaccurate motion vector (MV) usually lead to the distortion of reconstructed frame. In addition, most approaches ignore the spatial and channel redundancy. To solve above problems, we propose a motion-aware and spatial-temporal-channel contextual coding based video compression network (MASTC-VC), which learns the latent representation and uses variational autoencoders (VAEs) to capture the characteristics of intra-frame pixels and inter-frame motion. Specifically, we design a multiscale motion-aware module (MS-MAM) to estimate spatial-temporal-channel consistent motion vector by utilizing the multiscale motion prediction information in a coarse-to-fine way. On the top of it, we further propose a spatial-temporal-channel contextual module (STCCM), which explores the correlation of latent representation to reduce the bit consumption from spatial, temporal and channel aspects respectively. Comprehensive experiments show that our proposed MASTC-VC is surprior to previous state-of-the-art (SOTA) methods on three public benchmark datasets. More specifically, our method brings average 10.15% BD-rate savings against H.265/HEVC (HM-16.20) in PSNR metric and average 23.93% BD-rate savings against H.266/VVC (VTM-13.2) in MS-SSIM metric.	12pages,12 figures	None