Face anonymization preserving facial expressions and photometric realism

2026-03-18

AI Summary

This work addresses a critical limitation in existing face anonymization methods, which often neglect the preservation of facial expressions and photometric consistency—such as lighting direction and skin tone—thereby degrading downstream task performance. Building upon DeepPrivacy, the proposed framework introduces dense facial landmarks to retain expressive details and incorporates a lightweight post-processing module to modulate illumination and skin color. This approach is the first to systematically balance identity anonymity, expression fidelity, and photometric realism. Additionally, the study introduces novel evaluation metrics specifically designed to assess expression, lighting, and skin tone preservation. Experimental results on CelebA-HQ demonstrate that the method significantly outperforms current state-of-the-art techniques, achieving high anonymity and visual realism while substantially improving multi-dimensional feature fidelity.

Technology Category

• Computer Vision: Bias, Fairness & Privacy
• Machine Learning: Privacy
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy

Application Category

• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Responsible Web: Data and user privacy-enhancing technologies for the Web

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.

Problem

• face anonymization
• facial expressions
• photometric realism
• identity preservation
• privacy

Innovation

• face anonymization
• facial expression preservation
• photometric consistency
• dense facial landmarks
• lightweight post-processing