Disentangle Before Anonymize: A Two-stage Framework for Attribute-preserved and Occlusion-robust De-identification
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908344447401984 |
|---|---|
| author | Zhu, Mingrui Chen, Dongxin Wei, Xin Wang, Nannan Gao, Xinbo |
| author_facet | Zhu, Mingrui Chen, Dongxin Wei, Xin Wang, Nannan Gao, Xinbo |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_08786 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Disentangle Before Anonymize: A Two-stage Framework for Attribute-preserved and Occlusion-robust De-identification Zhu, Mingrui Chen, Dongxin Wei, Xin Wang, Nannan Gao, Xinbo Computer Vision and Pattern Recognition 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. |
| title | Disentangle Before Anonymize: A Two-stage Framework for Attribute-preserved and Occlusion-robust De-identification |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2311.08786 |