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

Inria Méditerranée1, Bocconi University2
INRIA Logo
Bocconi University Logo
AnonNET Pipeline

AnonNET: A unified framework for expression consistent anonymization in talking head videos.

Original | Source | Anonymized

Abstract

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 here a novel unified framework referred to as AnonNET, streamlined to de-identify a facial video, 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 the datasets VoxCeleb2, CelebV-HQ, and HDTF, which include diverse facial dynamics, demonstrate the effectiveness of AnonNET in obfuscating identity while retaining visual realism and temporal consistency.

Image Anonymization

Original | Anonymized
Original 1
Anonymized 1
Original 2
Anonymized 2
Original 3
Anonymized 3
Original 4
Anonymized 4
Original 5
Anonymized 5
Original 6
Anonymized 6
Original 7
Anonymized 7
Original 8
Anonymized 8
Original 9
Anonymized 9

Related Links

Our work builds upon and extends several approaches in face animation and anonymization.

LivePortrait provides a robust framework for face animation that we utilize in our pipeline.

LIA (Latent Image Animatior) offers an effective approach for image animation that we adapt for our anonymization framework.

BibTeX

@article{TBD,
  author    = {Egin, Anil and Tangherloni, Andrea and Dantcheva, Antitza},
  title     = {Now You See Me, Now You Don't: A Unified Framework for Expression Consistent Anonymization in Talking Head Videos},
  journal   = {TBD},
  year      = {2025},
}