ControlFace: Feature Disentangling for Controllable Face Swapping

ControlFace: Feature Disentangling for Controllable Face Swapping

Face swapping is an intriguing and intricate task in the field of computer vision. Currently, most mainstream face swapping methods employ face recognition models to extract identity features and inject them into the generation process. Nonetheless, such methods often struggle to effectively transfe...

Full description

Bibliographic Details
Main Authors: Xuehai Zhang, Wenbo Zhou, Kunlin Liu, Hao Tang, Zhenyu Zhang, Weiming Zhang, Nenghai Yu
Format: Article
Language:English
Published: MDPI AG 2024-01-01
Series:Journal of Imaging
Subjects:
face swapping
feature disentanglement
semantic hierarchy-based feature fusion
controllable identity feature transfer
Online Access:https://www.mdpi.com/2313-433X/10/1/21

Internet

https://www.mdpi.com/2313-433X/10/1/21

Similar Items