Introduction

• We are the 3D Motion and Rendering team of Applied Vision Lab, Institute for Intelligent Computing（通义实验室）, Alibaba Group, focusing on efficiently generating usable videos from text, image, video, and 3D model.

Open Source

• Video:
  • Coming soon.
• 3D Human:
  • https://aigc3d.github.io/HumanNormal
• 3D Scene:
  • https://aigc3d.github.io/freditor （ECCV 2024）
  • https://fangchuan.github.io/PanoContext-Former/ （CVPR 2024）
• 3D Object：
  • https://aigc3d.github.io/Sparse3D/ （ECCV 2024）
  • https://aigc3d.github.io/ConsistenTex/ （ECCV 2024）
  • https://aigc3d.github.io/VideoMV
  • https://yushuang-wu.github.io/IPoD/ （CVPR 2024 Hightlight）
  • https://aigc3d.github.io/richdreamer （CVPR 2024 Hightlight）
  • https://aigc3d.github.io/GPLD3D/ （CVPR 2024 Oral）

Open Project

• Large Scale Neural Rendering:
  • Project: https://aigc3d.github.io/landshop
• Video Character Replacement：
  • Project: https://aigc3d.github.io/motionshop
  • Demo: https://modelscope.cn/studios/Damo_XR_Lab/motionshop/summary
• 3D Object Generation：
  • Demo: https://modelscope.cn/studios/Damo_XR_Lab/3D_AIGC/summary

Data Set

• 3D Object Rendering Dataset：https://aigc3d.github.io/gobjaverse

Talent

• Reserch intern positions are open（Beijing、Hangzhou），research area：3D Avatar、3D Object Generation！
  • https://zhuanlan.zhihu.com/p/685816106
• Contact：[email protected]