Jian Wang

Jian Wang

Ph.D. student in Computer Vision

Max Planck Institute for Informatics

Biography

I’m Jian Wang, a 4th year Ph.D. student at D6 of Max Planck Institute for Informatics (MPI-INF), advised by Prof. Christian Theobalt. I am currently working on the topic of egocentric motion capture and am also interested in related topics including human motion generation and human performance capture. During my master’s study in ISCAS, I worked in the area of programming language and was fortunately supervised by Prof. Naijun Zhan. I also worked with Yichen Wei and Chi Zhang on the texture generation of the 3D human body during my internship in Face++. Prior to that, I was a student working on organic materials at Peking University.

You can also refer to my personal website in the group page.

As I'm nearing graduation, I am actively seeking a research scientist/engineer position :)

Interests
  • Egocentric Human Motion Capture
  • Computer Vision
  • Human Motion Generation
Education

  • PhD in Computer Science, 2020 - 2024

    Max Planck Institute for Informatics

  • MEng in Computer Science, 2016 - 2019

    Institute of Software, Chinese Academy of Sciences

  • BSc in Chemistry, 2012 - 2016

    Peking University

All Publications

Quickly discover relevant content by filtering publications.
Jian Wang, Zhe Cao, Diogo Luvizon, Lingjie Liu, Kripasindhu Sarkar, Danhang Tang, Thabo Beeler, Christian Theobalt (2023). Egocentric Whole-Body Motion Capture with FisheyeViT and Diffusion-Based Motion Refinement. In CVPR.

PDF Cite Project Arxiv

Jian Wang, Diogo Luvizon, Weipeng Xu, Lingjie Liu, Kripasindhu Sarkar, Christian Theobalt (2023). Scene-aware Egocentric 3D Human Pose Estimation.. In CVPR.

PDF Cite Code Project Video Supp. Mat.

Hiroyasu Akada, Jian Wang, Soshi Shimada, Masaki Takahashi, Christian Theobalt, Vladislav Golyanik (2022). UnrealEgo: A New Dataset for Robust Egocentric 3D Human Motion Capture.. In ECCV.

Cite Project

Jian Wang, Lingjie Liu, Weipeng Xu, Kripasindhu Sarkar, Christian Theobalt (2021). Estimating Egocentric 3D Human Pose in Global Space.. In ICCV (Oral).

Cite Project

Jian Wang, Lingjie Liu, Weipeng Xu, Kripasindhu Sarkar, Diogo Luvizon, Christian Theobalt (2021). Estimating Egocentric 3D Human Pose in the Wild with External Weak Supervision.. In CVPR.

Cite Project

See all publications

Experience

 
 
 
 
 
Research Intern
MPI-INF
November 2019 – April 2020 Germany
Egocentric motion capture.
 
 
 
 
 
Research Intern
Megvii Inc.
June 2018 – November 2018 China
Human texture generation from a single image.
 
 
 
 
 
Research Intern
Institute of Automation, Chinese Academy of Sciences
January 2018 – June 2018 China
Reinforcement learning for playing starcraft.
 
 
 
 
 
Research Intern
Baidu Inc.
January 2017 – June 2017 China
Developed the first version of Table OCR.

Contact