Yuhan Wang

Yuhan Wang

Ph.D. student of MMLab@NTU

Nanyang Technological University

Biography

My name is spelled 王宇晗 in Chinese.

I am a Ph.D. student in the College of Computing and Data Science (CCDS), Nanyang Technological University. I am a member of MMLab@NTU, advised by Prof. Chen Change Loy. My current research lies in 3D generation, human generation and video generation. I am currently a research intern at LightSpeed Studios, working with Zeyu Hu, Weikai Chen, and Xin Wang on 3D generation related topics.

Before joining NTU, I earned my bachelor degree from Chu Kochen Honors College, Zhejiang University. I had some wonderful research experience in Tencent Youtu Lab with Dr. Ying Tai and Junwei Zhu. I am also an ACMer, participated in six ACM ICPC/CCPC Asia Regional Contest, with four gold medals and two silver medals.

Interests
  • 3D Generation
  • Human Generation
  • Image and Video Generation
  • Face Manipulation
Education

  • PhD in Computer Science and Engineering, 2022 - Now

    Nanyang Technological University

  • BSc in Computer Science and Technology, 2017 - 2021

    Zhejiang University

Publications

MEAT: Multiview Diffusion Model for Human Generation on Megapixels with Mesh Attention
Yuhan Wang, Fangzhou Hong, Shuai Yang, Liming Jiang, Wayne Wu, Chen Change Loy
In 2025 Conference on Computer Vision and Pattern Recognition (CVPR 2025)
PDF Cite Code Project Page
MEAT: Multiview Diffusion Model for Human Generation on Megapixels with Mesh Attention
Towards Dense and Accurate Radar Perception Via Efficient Cross-Modal Diffusion Model
Ruibin Zhang, Donglai Xue, Yuhan Wang, Ruixu Geng, Fei Gao
In IEEE Robotics and Automation Letters. (RA-L)
PDF Cite Code Video Project Page
Towards Dense and Accurate Radar Perception Via Efficient Cross-Modal Diffusion Model
StyleInV: A Temporal Style Modulated Inversion Network for Unconditional Video Generation
Yuhan Wang, Liming Jiang, Chen Change Loy
In 2023 International Conference on Computer Vision (ICCV 2023)
PDF Cite Code Video Project Page
StyleInV: A Temporal Style Modulated Inversion Network for Unconditional Video Generation
HifiFace: 3D Shape and Semantic Prior Guided High Fidelity Face Swapping
Yuhan Wang, Xu Chen, Junwei Zhu, Wenqing Chu, Ying Tai, Chengjie Wang, Jilin Li, Yongjian Wu, Feiyue Huang, Rongrong Ji
In 2021 International Joint Conferences on Artificial Intelligence (IJCAI 2021)
PDF Cite Dataset Project Page
HifiFace: 3D Shape and Semantic Prior Guided High Fidelity Face Swapping
CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition
Yuge Huang, Yuhan Wang, Ying Tai, Xiaoming Liu, Pengcheng Shen, Shaoxin Li, Jilin Li, Feiyue Huang
In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2020)
PDF Cite Code
CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition

Experience

 
 
 
 
 
Research Intern
LightSpeed Studios, Tencent
Oct 2024 – Present Singapore

Research on

  • 3D generation foundation model - Geometry generation
  • Primitive-decomposed 3D Generation
 
 
 
 
 
Research Intern
Tencent Youtu
Oct 2020 – Nov 2021 Shanghai
Research on high fidelity face swapping algorithm.
 
 
 
 
 
Summer Research Assistant
ARoS Lab, North Carolina State University
Jul 2020 – Sep 2020 Remote
Research on Tracking-by-Detection Based Pedestrian Recognition in Infrared Video.
 
 
 
 
 
Research Intern
Tencent Youtu
Jul 2019 – Sep 2019 Shanghai

Research on

  • Neural Architecture Search on Face Classification Backbone
  • Margin-Mining Combined Deep Face Classification Loss

Honors

NVIDIA Hardware Grant Program, 2x A5000
NVIDIA Apr 2022
AISG PhD Fellowship
AISG Jan 2022
SenseTime Scholarship 2021
SenseTime Jan 2021
National Scholarship
Ministry of Education Nov 2020
ACM ICPC Asian Regional Contest Gold Medal
ACM ICPC Sep 2017 – Dec 2018
2018 Shenyang, 2017 Xi’an, 2017 Nanning, 2017 Hangzhou

Professional Services

Conference Reviewer:

  • AAAI 2024
  • ECCV 2024
  • CVPR 2025
  • ICCV 2025

Students Mentoring:

  • NTU Final Year Project (FYP): Cecelia Soh Yan Pei

Teaching

I am the teaching assistant of the following courses at NTU:

  • SC1003: Introduction to Computational Thinking and Programming, 2023 Fall
  • SC4242/CZ3007: Compiler Techniques, 2023 Spring
  • SC1003: Introduction to Computational Thinking and Programming, 2022 Fall

Skills

Language

Python, C, C++, Java

Research

PyTorch, CUDA

Chills

ACM, Basketball, Badminton, Go Game

Contact