Stars
VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold
Official code release for the PVSM paper: "From Rays to Projections: Better Inputs for Feed-Forward View Synthesis"
IDESplat: Iterative Depth Probability Estimation for Generalizable 3D Gaussian Splatting
[IJCV 2025] OPONeRF: One-Point-One NeRF for Robust Few-shot Rendering
Official implementation of "Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation".
offical repository of LiteVGGT: Boosting Vanilla VGGT via Geometry-aware Cached Token Merging
[ICLR 2026] FastVGGT: Fast Visual Geometry Transformer
[ICLR 2026] Streaming 4D Visual Geometry Transformer
Joint 3D Geometry Reconstruction and Motion Generation for 4D Synthesis from a Single Image
GenLit: Reformulating Single-Image Relighting as Video Generation
Reflection Removal through Efficient Adaptation of Diffusion Transformers
Official repository of "FMA-Net++: Motion- and Exposure-Aware Real-World Joint Video Super-Resolution and Deblurring"
Codebase for our paper "DenoiseGS: Gaussian Reconstruction Model for Burst Denoising"
Our paper 'CompEvent: Complex-valued Event-RGB Fusion for Low-light Video Enhancement and Deblurring' has been accepted at AAAI 2026.
Official repository of the "Clustered Error Correction with Grouped 4D Gaussian Splatting" (SIGGRAPH Asia 2025)
This is the project for 'Any2Caption', Interpreting Any Condition to Caption for Controllable Video Generation
Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.
[CVPR'25] StyleMaster: Stylize Your Video with Artistic Generation and Translation
IBGS: Image-Based Gaussian Splatting (NeurIPS2025)
[AAAI' 26]SparseSurf: Sparse-View 3D Gaussian Splatting for Surface Reconstruction
[TVCG2024] PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction
An implementation of DashGaussian, a powerful 3DGS training acceleration method. Accepted by CVPR 2025 (highlight).
Official Pytorch Implementation for "Time-to-Move: Training-Free Motion Controlled Video Generation via Dual-Clock Denoising"