This repository aims to document the interesting papers/blogs in different directions including Machine Learning, Computer Vision, NLP, Optimization, physics, etc.
- A non-local algorithm for image denoising
- Fast Image Deconvolution using Hyper-Laplacian Priors
- From Learning Models of Natural Image Patches to Whole Image Restoration
- Fields of Experts: A framework for learning image priors
- Learning Deep CNN Denoiser Prior for Image Restoration
- Deep Image Prior
- Machine Learning: A Probabilistic Perspective
- Fast Approximate Energy Minimization via Graph Cuts
- Diverse m-best solutions in markov random fields
- Conditional Random Fields as Recurrent Neural Networks
- Continuous Markov Random Fields for Robust Stereo Estimation
- Low-level Vision by Consensus in a Spatial Hierarchy of Regions
- 3D scene flow estimation with a piecewise rigid scene model
- Efficient Coarse-to-Fine PatchMatch for Large Displacement Optical Flow
- EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flow
- Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches
- Pyramid Stereo Matching Network
- PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume
- Surface Normals in the Wild
- Distinctive Image Features from Scale-Invariant Keypoints
- Video Google: A Text Retrieval Approach to Object Matching in Videos
- Histograms of Oriented Gradients for Human Detection
- Object Detection with Discriminatively Trained Part Based Models
- Rich feature hierarchies for accurate object detection and semantic segmentation (R-CNN)
- Fast R-CNN
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Simultaneous Detection and Segmentation
- Deep Watershed Transform for Instance Segmentation
- Unsupervised Learning of Video Representations using LSTMs
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
- Deep Residual Learning for Image Recognition
- You Only Look Once: Unified, Real-Time Object Detection
- YOLOv3: An Incremental Improvement
- Densely Connected Convolutional Networks
- CG2Real: Improving the Realism of Computer Generated Images using a Large Collection of Photographs
- Seam Carving for Content-Aware Image Resizing
- Image Quilting for Texture Synthesis and Transfer
- Poisson Image Editing
- Image Style Transfer Using Convolutional Neural Networks
- Context Encoders: Feature Learning by Inpainting
- Image-to-Image Translation with Conditional Adversarial Nets
- Sparse, Smart Contours to Represent and Edit Images
- Generative Adversarial Text-to-Image Synthesis
- Motion Magnification
- Phase-Based Video Motion Processing
- Super-Resolution from a Single Image
- Blind Deblurring Using Internal Patch Recurrence
- Blind Dehazing Using Internal Patch Recurrence
- Single Image Haze Removal Using Dark Channel Prior
- Revealing and Modifying Non-Local Variations in a Single Image
- Data-driven Hallucination of Different Times of Day from a Single Outdoor Photo
- The Bas-Relief Ambiguity
- From Shading to Local Shape
- Shape, Illumination and Reflectance from Shading
- Category-Specific Object Reconstruction from a Single Image
- Deriving intrinsic images from image sequences
- Recovering Intrinsic Images from a Single Image
- Shapecollage: occlusion-aware, example-based shape interpretation
- Discriminative Shape from Shading in Uncalibrated Illumination
- Shape Estimation in Natural Illumination
- Ground truth dataset and baseline evaluations for intrinsic image algorithms
- Intrinsic Images in the Wild
- Learning Ordinal Relationships for Mid-Level Vision
- CGIntrinsics: Better Intrinsic Image Decomposition through Physically-Based Rendering
- Single Image Intrinsic Decomposition without a Single Intrinsic Image
- Single-Shot Reflectance Measurement from Polarized Color Gradient Illumination
- Color Subspaces as Photometric Invariants
- A Dictionary-based Approach for Estimating Shape and Spatially-Varying Reflectance
- Near-Light Photometric Stereo using Circularly Placed Point Light Sources
- Deep Outdoor Illumination Estimation
- Learning to Predict Indoor Illumination from a Single Image
- Color Constancy by Learning to Predict Chromaticity from Luminance
- Convolutional Color Constancy
- Illuminant Spectra-based Source Separation Using Flash Photography
- Learning to Separate Multiple Illuminants in a Single Image
- Learning Sensor Multiplexing Design through Back-propagation
- Flash Photography Enhancement via Intrinsic Relighting
- Dark Flash Photography
- Burst Denoising with Kernel Prediction Networks
- Generalized Assorted Pixel Camera: Post-Capture Control of Resolution, Dynamic Range and Spectrum
- Single-Shot High Dynamic Range Imaging with Conventional Camera Hardware
- Unbounded High Dynamic Range Photography using a Modulo Camera
- A Layer-Based Restoration Framework for Variable-Aperture Photography
- U-Net: Convolutional Networks for Biomedical Image Segmentation
- Brain Tumor Segmentation and Radiomics Survival Prediction: Contribution to the BRATS 2017 Challenge
- Adversarial Regularizers in Inverse Problems
- Attention Is All You Need
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Learning Graph Structures with Transformer for Multivariate Time Series Anomaly Detection in IoT
- Multivariate Time-series Anomaly Detection via Graph Attention Network
- vanilla GAN
- Deep Convolutional GAN
- Wasserstein GAN
- TransGAN
- Spectral Normalization for Generative Adversarial Networks
- Multiple Instance Learning: A Survey of Problem Characteristics and Applications
- Attention-based Deep Multiple Instance Learning
- Dropout: A Simple Way to Prevent Neural Networks from Overfitting
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- The Little Engine that Could: Regularization by Denoising (RED)
- Plug-and-Play Methods Provably Converge with Properly Trained Denoisers
- Adam: A Method for Stochastic Optimization
- AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradients