alt text  

Dongze Li (李东泽)

Ph.D. Candidate
Center for Research on Intelligent Perception and Computing
National Lab of Pattern Recognition

Google Scholar  |  GitHub  
Email: dongze.li at cripac dot ia dot ac dot cn
Address: 95, Zhongguancun East Road, Beijing 100190, China


Biography

I am a Ph.D. Candidate of CRIPAC (led by Prof. Tieniu Tan), National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA) under the supervision of Prof. Tieniu Tan and Dr. Wei Wang. Before that, I received my Bachelor degree from Dalian University of Technology (DLUT) in 2020. My current research interests mainly lie in human centric generative modeling, e.g. Talking Face Generation, Personalized Video Generation and Face De-identification.

Education

alt text  

University of Chinese Academy of Sciences (UCAS)                                 Sep. 2020 - Jun. 2025 (Expected)
Ph.D. in Computer Applied Technology
Advisor: Prof. Tieniu Tan and Dr. Wei Wang


alt text  

Dalian University of Technology (DLUT)                                                   Sep. 2016 - Jun. 2020
B.Eng. in Computer Science and Technology

Selected Publications

alt text  

S^3D-NeRF: Single Shot Speech Driven Neural Radiance Field for High Fidelity Talking Head Synthesis
Dongze Li, Kang Zhao, Wei Wang, Yifeng Ma, Bo Peng, Yingya Zhang, Jing Dong
European Conference on Computer Vision (ECCV), 2024.
PDF

alt text  

AE-NeRF: Audio Enhanced Neural Radiance Field for Few Shot Talking Head Synthesis
Dongze Li, Kang Zhao, Wei Wang, Bo Peng, Yingya Zhang, Jing Dong and Tieniu Tan
AAAI Conference on Artificial Intelligence (AAAI), 2024.
PDF

alt text  

RiDDLE: Reversible and Diversified De-identification with Latent Encryptor
Dongze Li, Wei Wang, Kang Zhao, Jing Dong and Tieniu Tan
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
PDF | Code

alt text  

Exploring Adversarial Fake Images on Face Manifold
Dongze Li, Wei Wang, Hongxing Fan and Jing Dong
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021. Oral Presentation
PDF | Code