A Key-Driven Framework for Identity-Preserving Face Anonymization

TL;DR

This paper introduces a key-driven framework that generates virtual faces preserving head posture and expression for privacy, allowing identity recognition without exposing original images, balancing privacy and identifiability.

Contribution

The study proposes a novel framework combining head posture-preserving face generation and key-controlled authentication for identity-preserving face anonymization.

Findings

Effectively achieves facial anonymity and identifiability.

Generates virtual faces with preserved head posture and expression.

Enables original identity recognition without exposing original images.

Abstract

Virtual faces are crucial content in the metaverse. Recently, attempts have been made to generate virtual faces for privacy protection. Nevertheless, these virtual faces either permanently remove the identifiable information or map the original identity into a virtual one, which loses the original identity forever. In this study, we first attempt to address the conflict between privacy and identifiability in virtual faces, where a key-driven face anonymization and authentication recognition (KFAAR) framework is proposed. Concretely, the KFAAR framework consists of a head posture-preserving virtual face generation (HPVFG) module and a key-controllable virtual face authentication (KVFA) module. The HPVFG module uses a user key to project the latent vector of the original face into a virtual one. Then it maps the virtual vectors to obtain an extended encoding, based on which the virtual face is generated. By simultaneously adding a head posture and facial expression correction module, the virtual face has the same head posture and facial expression as the original face. During the authentication, we propose a KVFA module to directly recognize the virtual faces using the correct user key, which can obtain the original identity without exposing the original face image. We also propose a multi-task learning objective to train HPVFG and KVFA. Extensive experiments demonstrate the advantages of the proposed HPVFG and KVFA modules, which effectively achieve both facial anonymity and identifiability.