Stars
Elevate your AI research writing, no more tedious polishing ✨
Official implementation of OpenTrack.
HY-Motion model for 3D human motion or 3D character animation generation.
Masked Depth Modeling for Spatial Perception
Native and Compact Structured Latents for 3D Generation
End-to-end pipeline converting generative videos (Veo, Sora) to humanoid robot motions
GentleHumanoid: Whole body Motion Tracking with Compliance - Inference and Deploy
A Paper List for Humanoid Robot Learning.
A plug-and-play deploy framework for robots. Just deploy, just do.
An unofficial and simplified implementation of SIGGRAPH 2025 best paper nominate: CAST: Component-Aligned 3D Scene Reconstruction from an RGB Image, working in progress
[NeurIPS 2025] InternScenes: A Large-scale Interactive Indoor Scene Dataset with Realistic Layouts.
Isaac Lab API, powered by MuJoCo-Warp, for RL and robotics research.
Code for "Steerable Scene Generation with Post Training and Inference-Time Search", CoRL 2025
Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assets
Wan: Open and Advanced Large-Scale Video Generative Models
[SIGGRAPH Asia 2025 - TOG] Official implementation of MILo: Mesh-In-the-Loop Gaussian Splatting for Detailed and Efficient Surface Reconstruction
[ICLR 2025] From anything to mesh like human artists. Official impl. of "MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers"
[CVPR 2024] GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting
MapAnything: Universal Feed-Forward Metric 3D Reconstruction
[NeurIPS 2025] LiteReality: Graphics-Ready 3D Scene Reconstruction from RGB-D Scans
ViPE: Video Pose Engine for Geometric 3D Perception
[ICLR 2026] OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling
Official Repository of Event-Driven Storytelling with Multiple Lifelike Humans in a 3D Scene (ICCV 2025)