3D Facial
3D facial research focuses on creating realistic and expressive three-dimensional models of faces, primarily for applications in animation, virtual reality, and human-computer interaction. Current research emphasizes developing sophisticated models, often employing diffusion models, transformer networks, and graph neural networks, to generate highly realistic facial animations driven by audio or text descriptions, and to accurately reconstruct 3D facial geometry from images or videos, including nuanced expressions and emotional subtleties. These advancements are significantly improving the realism and expressiveness of digital avatars and virtual characters, with implications for fields ranging from entertainment to healthcare.
Papers
EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation
Ziqiao Peng, Haoyu Wu, Zhenbo Song, Hao Xu, Xiangyu Zhu, Jun He, Hongyan Liu, Zhaoxin Fan
Graphics Capsule: Learning Hierarchical 3D Face Representations from 2D Images
Chang Yu, Xiangyu Zhu, Xiaomei Zhang, Zhaoxiang Zhang, Zhen Lei