Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation

• Published in: Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 4174 - 4184
• Main Authors: Zhou, Hang, Sun, Yasheng, Wu, Wayne, Loy, Chen Change, Wang, Xiaogang, Liu, Ziwei
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2021
• Subjects: Aerospace electronics; Face recognition; Lips; Robustness; Speech coding; Speech recognition; Three-dimensional displays

While accurate lip synchronization has been achieved for arbitrary-subject audio-driven talking face generation, the problem of how to efficiently drive the head pose remains. Previous methods rely on pre-estimated structural information such as landmarks and 3D parameters, aiming to generate person...