Mingyi Shi

Mingyi Shi (史明镒)

Ph.D Student

The University of Hong Kong (HKU)

Email: myshi@cs.hku.hk

More Links:: Github, Publications

I'm currently a Ph.D. student from 11.2020 in the Department of Computer Science, working with Prof. Taku Komura. My research lies in Human Motion and Virtual Avatar, I hope diverse human motions can be captured and reenacted into the virtual world to bring more fantasies to our life. For that, I am developing an advanced motion capture system and learning the generation.

Before that, I got my B.Eng. and M.Sc. degree from Shandong University, supervised by Prof. Baoquan Chen. I spent three wonderful years(2017~2020) in Reality Capture Group in Beijing Film Academy and the CFCS in Peking University collaborated with the best research scientist Kfir Aberman.

I visited CYENS in Cyprus(2019), explored the deep learning tech in monocular motion capture system. In 2020, I have an internship at Electronic Arts for a project with AIDP and FIFA team.


Normalized Human Pose Features for Human Action Video Alignment

Jingyuan Liu, Mingyi Shi, Qifeng Chen, Hongbo Fu, Chiew-Lan Tai

ICCV 2021, oral

To appear

MotioNet: 3D Human Motion Reconstruction from Monocular Video with Skeleton Consistency

Mingyi Shi, Kfir Aberman, Andreas Aristidou, Taku Komura, Dani Lischinski, Daniel Cohen-Or, Baoquan Chen

ToG 2020, presented in SIGGRAPH Asia 2020


Deep Video-Based Performance Cloning

Kfir Aberman, Mingyi Shi, Jing Liao, Dani Lischinski, Baoquan Chen, Daniel Cohen-Or

Eurographics 2019


Neural Best-Buddies: Sparse Cross-Domain Correspondence

Kfir Aberman, Jing Liao, Mingyi Shi, Dani Lischinski, Baoquan Chen, Daniel Cohen-Or



Group optimization for multi-attribute visual embedding

Qiong Zeng, Wenzheng Chen, Zhuo Han, Mingyi Shi, Yanir Kleiman, Daniel Cohen-Or, Baoquan Chen, Yangyan Li

Visual Informatics 2018