Stars
[ICLR2026 - Oral] WAFT: Warping-Alone Field Transforms for Optical Flow
Code repository for "TrackEverything: Long Horizon Dense Tracking via De-Duplicating 3D Scene Representations"
Unofficial English translation of pengsida/learning_research aka Sida Peng's playbook for PhD students on doing research, writing papers, and giving talks.
[ICLR 2026] OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling
Arbitrary Reconstruction and Tracking of 4D Observation in the Wild
MegaFlow: Zero-Shot Large Displacement Optical Flow
Official implementation paper OmniX: Any-view and Any-time 4D Reconstruction via Feed-forward Trajectory Fields
VidMap: Exploiting Temporal Structure for Video-Based Structure-from-Motion (ECCV 2026)
[NeurIPS 2026 - Oral] Official implementation of Surflo: Consistent 3D Surface Flow Model with Global State.
Persistent remote applications for X11; screen sharing for X11, MacOS and MSWindows.
Zador-Pataki / rerun
Forked from rerun-io/rerunVisualize, query, and stream to train on multimodal robotics data.
Ranking and Covariances for Practical Learned Keypoints
[ECCV'26 Spotlight] ReSplat: Learning Recurrent Gaussian Splatting
[ICLR 2026] Official repository for "Real-3DQA"
The official Pytorch code for MoRo: Masked Modeling for Human Motion Recovery Under Occlusions
Geometry-grounded Point Transformer (CVPR 2026)
🚴 Call stack profiler for Python. Shows you why your code is slow!
[CVPR 2024] RoMa: Robust Dense Feature Matching; RoMa is the robust dense feature matcher capable of estimating pixel-dense warps and reliable certainties for almost any image pair.
[ICCV'25] 3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection
🌟A curated list of DUSt3R-related papers and resources, tracking recent advancements using this geometric foundation model.
[ECCV2024 - Oral, Best Paper Award Candidate] SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow
Any4D: Unified Feed-Forward Metric 4D Reconstruction
ViPE: Video Pose Engine for Geometric 3D Perception