GIM: Learning Generalizable Image Matcher From Internet Videos (ICLR 2024 Spotlight)

A curated list of awesome visual localization research works.

[CVPR 2023 Highlight] Perspective Fields for Single Image Camera Calibration

(latest updates and bug fixed) DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction

[CVPR 2024] Intraoperative 2D/3D registration via differentiable X-ray rendering

ID-Pose: Sparse-view Camera Pose Estimation by Inverting Diffusion Models

[AAAI2023] TopicFM: Robust, Efficient, and Interpretable Topic-Assisted Feature Matching

Neural Reprojection Error: Merging Feature Learning and Camera Pose Estimation (CVPR 2021)

[CVPR 2023] Two-view Geometry Scoring Without Correspondences

A Deep Learning Approach to Camera Pose Estimation

This demo uses a deep neural network and two generic cameras to perform 3D pose estimation.

[ICLR 2025] Official repo of "GS-CPR: Efficient Camera Pose Refinement via 3D Gaussian Splatting"

SoccerNet@CVPR | 1st place solution for Camera Calibration Challenge 2023

Given a map data (image + lidar), estimate the 6 DoF camera pose of the query image.

[ICRA'20] Robust 360-8PA": Redesigning The Normalized 8-point Algorithm for 360-FoV Images

Python tools for Generating and working metric 3D depth videos, 3D stereo video, side by side stereo video. Using 3d rendering and monocular depth estimation models and other ML models.

[ECCV 2024] SRPose: Two-view Relative Pose Estimation with Sparse Keypoints

Datasets for long-term visual localization with sequential images in large-scale spaces

A CNN based Depth, Optical Flow, Flow Uncertainty and Camera Pose Prediction pipeline

Python code to estimate depth using stereo vision.