CFA-Net: Controllable Face Anonymization Network with Identity Representation Manipulation
This addresses privacy protection for individuals in computer vision applications, but appears incremental as it builds on existing identity disentanglement methods.
The paper tackles the problem of de-identifying faces in images and videos while preserving data utility, proposing CFA-Net to generate various anonymized faces by manipulating identity vectors, with results showing superiority in visual quality and anonymization validity.
De-identification of face data has drawn increasing attention in recent years. It is important to protect people's identities meanwhile keeping the utility of the data in many computer vision tasks. We propose a Controllable Face Anonymization Network (CFA-Net), a novel approach that can anonymize the identity of given faces in images and videos, based on a generator that can disentangle face identity from other image contents. We reach the goal of controllable face anonymization through manipulating identity vectors in the generator's identity representation space. Various anonymized faces deriving from an original face can be generated through our method and maintain high similarity to the original image contents. Quantitative and qualitative results demonstrate our method's superiority over literature models on visual quality and anonymization validity.