I am a Research Scientist at ByteDance in San Jose, USA. Prior to this, I worked as a Research Scientist at Tencent with Dr. Gang Yu for about three years. I received my doctoral degree from University of Chinese Academy Sciences (ShanghaiTech) Visual Intelligent Center (VIC) under the supervision of Prof. Jingyi Yu.

My research interests focus on Computer Vision for Graphics. I have a great passion on new things and new ideas, my goal is to create Generative AI, which is about humans, used for humans, and benefits humans.

Interests
  • Generative AI
  • Computer Vision for Graphics
  • Human Motion Generation
  • 3D Foundation Models
  • Multimodal Models
Services
  • [Conference Reviewer]
    SIGGRAPH, CVPR, ICCV, ECCV, AAAI
  • [Journal Reviewer]
    TPAMI, TIP, IJCV, TMM
Collaborations
  • Welcome discussions from academia and industry, especially regarding technology implementation and real-world impact. Feel free to reach out via email.
  • I currently have internship positions available with the goal of conducting cutting-edge research in artificial intelligence. If you are interested, please send me an email.
News
  • [2024/09] MeshXL and 3DET-Mamba accepted to NeurIPS 2024, congrats to Sijin Chen and Mingshen Li
  • [2024/07] Joint ByteDance as a Research Scientist in San Jose, USA
  • [2024/06] We introduce MeshXL, a 3D fundamental model for mesh generation
  • [2024/04] Vote2Cap-DETR++ is accepted by T-PAMI 2024, congrats to Sijin Chen
  • [2024/02] 3 papers accepted at CVPR 2024, congrats to Paint3D, LL3DA, OMG
  • [2024/01] TapMo is accepted by ICLR 2024, congrats to Jiaxu Zhang
  • [2023/12] We introduce Paint3D, a lighting-less texture diffusion model.
  • [2023/12] We introduce AppAgent, a multimodal agent for smartphone apps.
  • [2023/11] We introduce ShapeGPT, a multimodal LLM for 3D shape generation.
  • [2023/11] We introduce LL3DA and M3DBench, a multimodal-language 3D assistant and benchmark.
  • [2023/09] 3 papers accepted at NeurIPS 2023
  • [2023/07] 1 paper accepted at ICCV 2023
  • [2023/02] 2 papers accepted at CVPR 2023
  • [2022/02] Join Tencent as a Research Scientist
  • [2022/01] Receive my Ph.D. degree
  • [2021/10] TightCap will be presented at ACM SIGGRAPH 2022

Publications

.js-id-selected
MeshXL: Neural Coordinate Field for Generative 3D Foundation Models
Paint3D: Paint Anything 3D with Lighting-less Texture Diffusion Models
TightCap: 3D Human Shape Capture with Clothing Tightness Field
Neural Free-Viewpoint Performance Rendering under Complex Human-object Interactions
ChallenCap: Monocular 3D Capture of Challenging Human Performances using Multi-Modal References
Sparse Photometric 3D Face Reconstruction Guided by Morphable Models

Experiences

 
 
 
 
 
ByteDance | 字节跳动
Research Scientist
July 2024 – Present San Jose, Bay Area
Research Scientist at Intelligent Creation Lab, focusing on Multi-modal Human Foundation Models and Agents.
 
 
 
 
 
Tencent | 腾讯
Research Scientist
February 2022 – June 2024 Shanghai
Research Scientist at QQ Image Lab, received two Outstanding performances and Tencent STAR Award 2023.
 
 
 
 
 
Tencent | 腾讯
Research Scientist Intern
November 2020 – May 2021 Shanghai
Research Scientist Intern at Tencent YouTuLab in 2020, focusing on the 3D human body reconstruction.
 
 
 
 
 
DGene Digital Technology Inc. | 叠境数字
Research Engineer Intern
July 2018 – December 2019 Shanghai
Research Engineer Intern at DGene Digital Technology Inc., my supervisor’s start-up, for world digitalization. I won the Best Outstanding Intern Award in 2018 for leading the mobile virtual fitting project.
 
 
 
 
 
Deerev  | 飞路
Software Engineer Summer Intern
June 2014 – September 2014 Shanghai
Software Engineer Intern in the Mobile App design Group, where I worked on system design and software testing.

Contact