JIAZHI (JAX) GUAN
官佳智

Ph.D.

Dept. of Computer Vision Technology (VIS)
Baidu Inc.
Email: guanjz20 [at] outlook.com
[Google Scholar] [Github]

Jiazhi Guan

Biography

Jiazhi Guan is currently an R&D Engineer at Baidu Inc. (VIS), where he focuses on research and development in digital human animation and generation. He received his Ph.D. in Computer Science and Technology from Tsinghua University, under the supervision of Prof. Youjian Zhao. Prior to that, he earned his Bachelor's degree from Wuhan University of Technology in 2020.

Experiences

R&D Engineer | Baidu Inc. VIS, Shenzhen Jun. 2025 – Present
Topic: Digital Human Animation/Generation
Visiting Student | S-Lab, Nanyang Technological University, Singapore Oct. 2024 – Jan. 2025
Topic: Body Animation
Advisor: Ziwei Liu
Research Intern | Baidu Inc. VIS, Beijing Nov. 2021 – Jun. 2025
Topic: Facial Animation, Body Animation
Advisor: Hang Zhou

Selected Publications

*: equal contribution | †: Corresponding author

AudCast: Audio-Driven Human Video Generation by Cascaded Diffusion Transformers
Jiazhi Guan, Kaisiyuan Wang, Zhiliang Xu, Quanwei Yang, Yasheng Sun, Shengyi He, Borong Liang, Yukang Cao, Yingying Li, Haocheng Feng, Errui Ding, Jingdong Wang, Youjian Zhao†, Hang Zhou†, Ziwei Liu†
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025.
Project PDF
TALK-Act: Enhance Textural-Awareness for 2D Speaking Avatar Reenactment with Diffusion Model
Jiazhi Guan, Quanwei Yang, Kaisiyuan Wang, Hang Zhou†, Shengyi He, Zhiliang Xu, Haocheng Feng, Errui Ding, Jingdong Wang, Hongtao Xie, Youjian Zhao†, Ziwei Liu
SIGGRAPH Asia Conference Proceedings (SIGGRAPH Asia), 2024.
Project PDF
ReSyncer: Rewiring Style-based Generator for Unified Audio-Visually Synced Facial Performer
Jiazhi Guan*, Zhiliang Xu*, Hang Zhou†, Kaisiyuan Wang, Shengyi He, Zhanwang Zhang, Borong Liang, Haocheng Feng, Errui Ding, Jingtuo Liu, Jingdong Wang, Youjian Zhao†, Ziwei Liu
European Conference on Computer Vision (ECCV, Oral), 2024.
Project PDF
StyleSync: High-Fidelity Generalized and Personalized Lip Sync in Style-based Generator
Jiazhi Guan*, Zhanwang Zhang*, Hang Zhou†, Tianshu Hu†, Kaisiyuan Wang, Dongliang He, Haocheng Feng, Jingtuo Liu, Errui Ding, Ziwei Liu, Jingdong Wang
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
Project PDF
Adversarial Robust Safeguard for Evading Deep Facial Manipulation
Jiazhi Guan, Yi Zhao†, Zhuoer Xu, Changhua Meng, Ke Xu, Youjian Zhao†
Association for the Advancement of Artificial Intelligence (AAAI), 2024
PDF Video
Dual-Modality Co-Learning for Unveiling Deepfake in Spatio-Temporal Space
Jiazhi Guan, Hang Zhou, Zhizhi Guo, Tianshu Hu, Lirui Deng, Chengbin Quan, Meng Fang, Youjian Zhao†
ACM International Conference on Multimedia Retrieval (ICMR, Best Paper Candidate), 2023
PDF
Delving into Sequential Patches for Deepfake Detection
Jiazhi Guan, Hang Zhou, Zhibin Hong, Errui Ding, Jingdong Wang, Chengbin Quan, Youjian Zhao†
Conference on Neural Information Processing Systems (NeurIPS), 2022.
PDF Video
Detecting Deepfake by Creating Spatio-Temporal Regularity Disruption
Jiazhi Guan, Hang Zhou, Mingming Gong, Errui Ding, Jingdong Wang, Youjian Zhao†
Arxiv: 2207.10402
PDF

Honors and Awards

Overall Excellence Scholarship, Tsinghua University
2022,2023,2024
Outstanding Graduate, Hubei Provinces
2020
National Scholarship, Ministry of Education, China
2017,2018,2019

Professional Activities

Conference Reviewer of: CVPR, ICCV, NeurIPS, ICML and ICLR.

Teaching

TA of Digital Logic Circuit, DCST, Tsinghua University Spring
2021-2024