Shuai Fan
Research Subjects
Shuai Fan has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Chenpeng Du
MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing; X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China
1 shared publication - Feilong Chen
AISpeech Ltd, Shanghai, China
1 shared publication - Kai Yu
Shanghai Jiao Tong University, Shanghai, China
1 shared publication - Qi Chen
X-LANCE lab, Shanghai Jiao Tong University, Shanghai, China
1 shared publication - Tao Liu
X-LANCE lab, Shanghai Jiao Tong University, Shanghai, China
1 shared publication - Xie Chen
Shanghai Jiao Tong University, Shanghai Innovation Institute, Shanghai, China
1 shared publication
Latest Publications
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 6696-6705
AniTalker: Animate Vivid and Diverse Talking Faces through Identity-Decoupled Facial Motion Encoding
The paper introduces AniTalker, an innovative framework designed to generate lifelike talking faces from a single portrait. Unlike existing models that primarily focus on verbal cues such as lip synchronization and fail to capture the complex dynamics of facial expressions and nonverbal cues, AniTalker employs a universal motion representation. This innovative representation effectively captures a wide range of facial dynamics, including subtle expressions and head movements. AniTalker enhances motion depiction through two self-supervised learning strategies: the first involves reconstructing target video frames from source frames within the same identity to learn subtle motion representations, and the second develops an identity encoder using metric learning while actively minimizing mutual information between the identity and motion encoders. This approach ensures that the motion representation is dynamic and devoid of identity-specific details, significantly reducing the need for labeled data. Additionally, the integration of a diffusion model with a variance adapter allows for the generation of diverse and controllable facial animations. This method not only demonstrates AniTalker's capability to create detailed and realistic facial movements but also underscores its potential in crafting dynamic avatars for real-world applications. Synthetic results can be viewed at https://github.com/X-LANCE/AniTalker.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 6696-6705
Open AccessAniTalker: Animate Vivid and Diverse Talking Faces through Identity-Decoupled Facial Motion Encoding
The paper introduces AniTalker, an innovative framework designed to generate lifelike talking faces from a single portrait. Unlike existing models that primarily focus on verbal cues such as lip synchronization and fail to capture the complex dynamics of facial expressions and nonverbal cues, AniTalker employs a universal motion representation. This innovative representation effectively captures a wide range of facial dynamics, including subtle expressions and head movements. AniTalker enhances motion depiction through two self-supervised learning strategies: the first involves reconstructing target video frames from source frames within the same identity to learn subtle motion representations, and the second develops an identity encoder using metric learning while actively minimizing mutual information between the identity and motion encoders. This approach ensures that the motion representation is dynamic and devoid of identity-specific details, significantly reducing the need for labeled data. Additionally, the integration of a diffusion model with a variance adapter allows for the generation of diverse and controllable facial animations. This method not only demonstrates AniTalker's capability to create detailed and realistic facial movements but also underscores its potential in crafting dynamic avatars for real-world applications. Synthetic results can be viewed at https://github.com/X-LANCE/AniTalker.