Human Face
Human face research spans diverse fields, aiming to understand and replicate facial features, expressions, and their associated social and psychological implications. Current research focuses on developing advanced generative models (e.g., StyleGAN, diffusion models) for realistic 3D face generation from single images and audio, often incorporating techniques like mesh attention and conditional flow matching to enhance realism and control. These advancements have significant implications for applications ranging from virtual reality and animation to forensic science and the detection of AI-generated media, while also raising ethical concerns regarding privacy and potential misuse.
Papers
Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editing
Hanhui Wang, Yihua Zhang, Ruizheng Bai, Yue Zhao, Sijia Liu, Zhengzhong Tu
Revisiting Marr in Face: The Building of 2D--2.5D--3D Representations in Deep Neural Networks
Xiangyu Zhu, Chang Yu, Jiankuo Zhao, Zhaoxiang Zhang, Stan Z. Li, Zhen Lei