Now You See Me, Now You Don't: A Unified Framework for Expression Consistent Anonymization in Talking Head Videos

Face video anonymization is aimed at privacy preservation while allowing for the analysis of videos in a number of computer vision downstream tasks such as expression recognition, people tracking, and action recognition. We propose a novel unified framework referred to as AnonNET, streamlined to de-identify facial videos while preserving age, gender, race, pose, and expression of the original video. Specifically, we inpaint faces by a diffusion-based generative model guided by high-level attribute recognition and motion-aware expression transfer. We then animate de-identified faces by video-driven animation, which accepts the de-identified face and the original video as input. Extensive experiments on VoxCeleb2, CelebV-HQ, and HDTF demonstrate the effectiveness of AnonNET in obfuscating identity while retaining visual realism and temporal consistency.

In IEEE/CVF International Conference on Computer Vision (ICCV) Workshops — Computer Vision for Biometrics, Identity & Behaviour (CV4BIOM)