#
Lists (3)
Starred repositories
MapAnything: Universal Feed-Forward Metric 3D Reconstruction
EO: Open-source Unified Embodied Foundation Model Series
[NeurIPS 2025 (Spotlight)] The implementation for the paper "4DGT Learning a 4D Gaussian Transformer Using Real-World Monocular Videos"
SpatialVID: A Large-Scale Video Dataset with Spatial Annotations
[CVPR 2024] On the Content Bias in Fréchet Video Distance
ReconViaGen: Towards Accurate Multi-view 3D Object Reconstruction via Generation
Official Implementation of paper "St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World"
Code for FastVGGT: Training-Free Acceleration of Visual Geometry Transformer
[NeurIPS 2024] Official implementation of NeurIPS 2024 paepr "Flow Priors for Linear Inverse Problems via Iterative Corrupted Trajectory Matching"
Official code for PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking (ICCV 2023)
Official Repository of "ROSE: Remove Objects with Side Effects in Videos"
Visualize PyTorch tensors with a single line of code.
🔥🔥 Open-sourced unified customization model
[ICCV 2025 Oral] MVTracker: Multi-view 3D Point Tracking
The official code of "Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning"
Implementation of "S^2-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models"
Frontier Multimodal Foundation Models for Image and Video Understanding
Tracking the latest and greatest research papers on video generation.
Official Repository of "OmniTry: Virtual Try-On Anything without Masks"
A survey for visual generation alignment
Mesh Silksong: Auto-Regressive Mesh Generation as Weaving Silk
Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)