Mingyi Shi

Mingyi Shi (史明镒)

Ph.D Student

The University of Hong Kong (HKU)

Email: myshi@cs.hku.hk

More Links:: GitHub, Scholar, LinkedIn

About Me

I'm currently a final-Year Ph.D. student in the Department of Computer Science, working with Prof. Taku Komura. My research focuses on ML-based Character Animation and LifeLong Digital Humans. I'm passionate about capturing and reenacting vivid human behaviors and emotions into virtual worlds to enhance our digital experiences. To achieve this, I am developing various advanced motion capture systems and motion generation frameworks.

Before joining HKU, I received my B.Eng. and M.Sc. degrees from Shandong University, supervised by Prof. Baoquan Chen. I spent three wonderful years (2017-2020) at the Reality Capture Group in Beijing Film Academy and the CFCS in Peking University, collaborating with research scientist Kfir Aberman.

Experiences

Publications

🎧 MOSPA: Spatial Audio-Driven Human Motion Generation

Shuyang Xu, Zhiyang Dou*#, Mingyi Shi, Liang Pan, Leo Ho, Jingbo Wang, Yuan Liu, Cheng Lin, Yuexin Ma,
Wenping Wang#, Taku Komura#

* Joint first author; # Corresponding authors

ArXiv 2025

[webpage] [paper] [video] [code] [bibTex]

InterAct: A Large-Scale Dataset of Dynamic, Expressive and Interactive Activities between Two People in Daily Scenarios

Leo Ho*, Yinghao Huang* , Dafei Qin, Mingyi Shi, Wangpok Tse, Wei Liu, Junichi Yamagishi, Taku Komura

SCA 2025

* Joint first author

[webpage] [paper] [video] [dataset] [bibTex]

Taming Diffusion Probabilistic Models for Character Control

Rui Chen*, Mingyi Shi* , Shaoli Huang, Ping Tan, Taku Komura, Xuelin Chen

SIGGRAPGH 2024, Featured in Technical Papers Video Trailer!

* Joint first author

[webpage] [paper] [code] [exe] [bibTex]

PhaseMP: Robust 3D Pose Estimation via Phase-conditioned Human Motion Prior

Mingyi Shi, Sebastian Starke, Yuting Ye, Taku Komura, Jungdam Won

ICCV 2023

[webpage] [paper] [code] [bibTex]

Normalized Human Pose Features for Human Action Video Alignment

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

ICCV 2021, oral

[paper] [supp] [bibTex]

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

[webpage][paper][video][code] [bibTex]

Deep Video-Based Performance Cloning

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

Eurographics 2019

[paper][video] [bibTex]

Neural Best-Buddies: Sparse Cross-Domain Correspondence

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

SIGGRAPH 2018

[webpage][paper][video][code] [bibTex]

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

[paper] [bibTex]

Academic Service

I help to review papers for: