About Me

I'm currently a Research Lead heading the Graphics AI team at Kuaishou Technology (Kwai Inc.). Previously I was a Sr. Research Scientist at Snap Research. Prior to that, I was a Senior Research Engineer at Activision Central Tech working on facial performance capture for game production. From 2012 to 2015, I was a postdoc researcher at UBC and USC working with Prof. Alla Sheffer and Prof. Hao Li respectively. I obtained my Ph.D. in Computer Science from Institute for Advanced Study of Tsinghua University in 2012, under the supervision of Dr. Baining Guo and Dr. Li-Yi Wei. I received my B.S. in Mathematics and Physics from Fundamental Science Class of Tsinghua University in 2007.


Had one paper accepted by ECCV 2020 about monucular depth estimation.
Had one paper accepted by CVPR 2020 about object detection.
Had one paper accepted by ACM Transactions on Graphics (TOG) about 3D scene synthesis.
Had one paper accepted by AAAI 2020 about image aesthetic assessment.
Had one paper accepted by IEEE Transactions on Visualization and Computer Graphics (TVCG) about visual summarization.
Had one paper accepted by IEEE Transactions on Multimedia with a two-word title.
Had one paper accepted by ICML 2019 about few-shot learning.
Had one paper accepted by ACM/EG Expressive Symposium about real-time portrait stylization.
Had one paper accepted by ICME 2019 about low-light image denoising.
Joined Kwai Inc. as a Research Lead.

Work Experience

  • Mar 2019 ~ Present
    Research Lead
  • Nov 2016 ~ Feb 2019
    Sr. Research Engineer/Scientist
  • July 2015 ~ Nov 2016
    Senior Computer Vision Research Engineer
  • Oct 2013 ~ June 2015
    Postdoctoral Scholar in Geometric Capture Lab

Other Positions

  • June 2014 ~ Aug 2014
    Research and Development Intern
  • Aug 2011 ~ Feb 2012
    Visiting student in ALICE team


publication gallery

Professional Activities

Research Interests

I have been focusing on democratizing visual content creation since I started my PhD in 2007. My reseach interests lie in the joint field of computer graphics and computer vision, including but not limited to deep generative models, image & video manipulation, motion capture, human digitization, face tracking, 3D understanding & reconstruction, data-driven animation, procedural modeling, digital geometry processing, and texture synthesis.