Stars
DreamX-World: A General-Purpose Interactive World Model
Training code for CVPR 2026 paper: RigMo: Unifying Rig and Motion Learning for Generative Animation
Office inference code for World Tracing (object/scene/dynamic). Live demos: https://haoz19.github.io/world-tracing-page/
Redirect4D-Bench: A Scalable Benchmark for Camera Redirection of Monocular Dynamic Videos with Pseudo-4D Ground Truth
[ICCV 2025] Official code for AnimateAnyMesh: A Feed-Forward 4D Foundation Model for Text-Driven Universal Mesh Animation
Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets
Physics-based rigging with MPM for realistic character animation. ICCV 2025.
[NeurIPS 2025 Spotlight] A Native Multimodal LLM for 3D Generation and Understanding
A suite of GUI tools for extracting and modifying OVL and OVS archives, as well as editing the associated in-house file formats. Also includes a model plugin for Blender. For downloads, guides, and…
Wan: Open and Advanced Large-Scale Video Generative Models
HunyuanVideo: A Systematic Framework For Large Video Generation Model
Open-Sora: Democratizing Efficient Video Production for All
Official implementation of ATI: Any Trajectory Instruction for Controllable Video Generation. https://arxiv.org/pdf/2505.22944
Lightweight Python framework that provides a high-level API for creating and rendering scenes with Blender.
Fine-tune SAM (Segment Anything Model) for computer vision tasks such as semantic segmentation, matting, detection ... in specific scenarios
Official Implementation of paper "A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence"
Code for "GVHMR: World-Grounded Human Motion Recovery via Gravity-View Coordinates", Siggraph Asia 2024, TPAMI 2026
🌊 [ECCV'24 Oral] MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images
A vector-quantized periodic autoencoder (VQ-PAE) for motion alignment across different morphologies with no supervision [SIGGRAPH 2024]
[CVPR 2024] SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusion
Official implementation of "Mesh-Based Adapting and Modification of Gaussian Splatting"
[CVPR 2024 Highlight] PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics
Code repository for our paper DiffCloth: Differentiable Cloth Simulation with Dry Frictional Contact
Code for CVPR2023 paper "HOOD: Hierarchical Graphs for Generalized Modelling of Clothing Dynamics"
[ECCV'24] GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image
[ICCV 2023] SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesis
InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models
HAHA: Highly Articulated Gaussian Human Avatars with Textured Mesh Prior