Disentangle Before Anonymize: A Two-stage Framework for Attribute-preserved and Occlusion-robust De-identification

TL;DR

This paper introduces a two-stage face de-identification framework that effectively preserves attributes and enhances robustness to occlusions, outperforming existing methods in quality and detail fidelity.

Contribution

The paper proposes a novel two-stage framework with modules for attribute retention and reversible anonymization, addressing limitations of simultaneous training.

Findings

Outperforms state-of-the-art de-identification methods

Achieves high-quality anonymization with attribute preservation

Demonstrates robustness to occlusions in experiments

Abstract

In an era where personal photos are easily leaked and collected, face de-identification is a crucial method for protecting identity privacy. However, current face de-identification techniques face challenges in preserving attribute details and often produce anonymized results with reduced authenticity. These shortcomings are particularly evident when handling occlusions,frequently resulting in noticeable editing artifacts. Our primary finding in this work is that simultaneous training of identity disentanglement and anonymization hinders their respective effectiveness.Therefore, we propose "Disentangle Before Anonymize",a novel two-stage Framework(DBAF)designed for attributepreserved and occlusion-robust de-identification. This framework includes a Contrastive Identity Disentanglement (CID) module and a Key-authorized Reversible Identity Anonymization (KRIA) module, achieving faithful attribute preservation and high-quality identity anonymization edits. Additionally, we introduce a Multiscale Attentional Attribute Retention (MAAR) module to address the issue of reduced anonymization quality under occlusions.Extensive experiments demonstrate that our method outperforms state-of-the-art de-identification approaches, delivering superior quality, enhanced detail fidelity, improved attribute preservation performance, and greater robustness to occlusions.