Face anonymization preserving facial expressions and photometric realism

TL;DR

This paper introduces a face anonymization method that preserves facial expressions and photometric attributes like lighting and skin tone, enhancing privacy while maintaining data utility for downstream tasks.

Contribution

The work extends DeepPrivacy by incorporating facial landmarks and post-processing modules to better retain expressions and photometric consistency in anonymized faces.

Findings

Improved realism and expression fidelity in anonymized faces.

Enhanced preservation of lighting and skin tone attributes.

Outperforms state-of-the-art baselines in key evaluation metrics.

Abstract

The widespread sharing of face images on social media platforms and in large-scale datasets raises pressing privacy concerns, as biometric identifiers can be exploited without consent. Face anonymization seeks to generate realistic facial images that irreversibly conceal the subject's identity while preserving their usefulness for downstream tasks. However, most existing generative approaches focus on identity removal and image realism, often neglecting facial expressions as well as photometric consistency -- specifically attributes such as illumination and skin tone -- that are critical for applications like relighting, color constancy, and medical or affective analysis. In this work, we propose a feature-preserving anonymization framework that extends DeepPrivacy by incorporating dense facial landmarks to better retain expressions, and by introducing lightweight post-processing modules that ensure consistency in lighting direction and skin color. We further establish evaluation metrics specifically designed to quantify expression fidelity, lighting consistency, and color preservation, complementing standard measures of image realism, pose accuracy, and re-identification resistance. Experiments on the CelebA-HQ dataset demonstrate that our method produces anonymized faces with improved realism and significantly higher fidelity in expression, illumination, and skin tone compared to state-of-the-art baselines. These results underscore the importance of feature-aware anonymization as a step toward more useful, fair, and trustworthy privacy-preserving facial data.