- We are the 3D Motion and Rendering team of Applied Vision, Tongyi Lab（通义实验室）, Alibaba Group, focusing on efficiently generating usable videos from text, image, video, and 3D model.
- Research intern positions are open（Beijing、Hangzhou），research area：3D Avatar、3D Object Generation！
- Contact：[email protected]
- Large Human Model:
- https://github.com/aigc3d/LHM (ICCV 2025)
- https://github.com/aigc3d/LHM-plusplus (2025)
- https://github.com/aigc3d/LHM_Track (2025)
- Large Avatar Model:
- 3D Avatar:
- https://lhyfst.github.io/balancehead/ (ICLR2026)
- https://github.com/aigc3d/HyPlaneHead (NeurIPS 2025)
- https://github.com/aigc3d/AniGS （CVPR 2025）
- https://aigc3d.github.io/LaMP （ICLR 2025）
- https://aigc3d.github.io/mogents （NIPS 2024）
- https://aigc3d.github.io/HumanNormal （2024）
- https://modelscope.cn/models/Damo_XR_Lab/cv_human_68-facial-landmark-detection （2024）
- 3D Object：
- https://github.com/aigc3d/MCMat （2024）
- https://aigc3d.github.io/richdreamer （CVPR 2024 Hightlight）
- https://yushuang-wu.github.io/IPoD/ （CVPR 2024 Hightlight）
- https://luyues.github.io/mvimgnet2/ （SIGGRAPH Asia 2024 Journal Track)
- 3D Perception:
- https://stable-x.github.io/StableNormal/ （SIGGRAPH Asia 2024 Journal Track)
- https://jukgei.github.io/project/gic/ （NIPS 2024 Oral）
- 3D Object：
- https://aigc3d.github.io/Sparse3D/ （ECCV 2024）
- https://aigc3d.github.io/ConsistenTex/ （ECCV 2024）
- https://aigc3d.github.io/VideoMV （2024）
- https://aigc3d.github.io/GPLD3D/ （CVPR 2024 Oral）
- 3D Scene:
- https://aigc3d.github.io/freditor （ECCV 2024）
- https://fangchuan.github.io/PanoContext-Former/ （CVPR 2024）
- Large Scale Neural Rendering:
- Project: https://aigc3d.github.io/landshop
- Video Character Replacement：
- 3D Object Generation：
- Multi-view Images Dataset：https://luyues.github.io/mvimgnet2/ （SIGGRAPH Asia 2024 Journal Track)
- 3D Object Rendering Dataset：https://aigc3d.github.io/gobjaverse
- 3D Human Rendering Dataset：https://aigc3d.github.io/HumanNormal/#dataset-section