G2Face: High-Fidelity Reversible Face Anonymization via Generative and Geometric Priors

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Haoxin, Xu, Xuemiao, Xu, Cheng, Zhang, Huaidong, Qin, Jing, Wang, Yi, Heng, Pheng-Ann, He, Shengfeng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910569707077632
author Yang, Haoxin
Xu, Xuemiao
Xu, Cheng
Zhang, Huaidong
Qin, Jing
Wang, Yi
Heng, Pheng-Ann
He, Shengfeng
author_facet Yang, Haoxin
Xu, Xuemiao
Xu, Cheng
Zhang, Huaidong
Qin, Jing
Wang, Yi
Heng, Pheng-Ann
He, Shengfeng
contents Reversible face anonymization, unlike traditional face pixelization, seeks to replace sensitive identity information in facial images with synthesized alternatives, preserving privacy without sacrificing image clarity. Traditional methods, such as encoder-decoder networks, often result in significant loss of facial details due to their limited learning capacity. Additionally, relying on latent manipulation in pre-trained GANs can lead to changes in ID-irrelevant attributes, adversely affecting data utility due to GAN inversion inaccuracies. This paper introduces G\textsuperscript{2}Face, which leverages both generative and geometric priors to enhance identity manipulation, achieving high-quality reversible face anonymization without compromising data utility. We utilize a 3D face model to extract geometric information from the input face, integrating it with a pre-trained GAN-based decoder. This synergy of generative and geometric priors allows the decoder to produce realistic anonymized faces with consistent geometry. Moreover, multi-scale facial features are extracted from the original face and combined with the decoder using our novel identity-aware feature fusion blocks (IFF). This integration enables precise blending of the generated facial patterns with the original ID-irrelevant features, resulting in accurate identity manipulation. Extensive experiments demonstrate that our method outperforms existing state-of-the-art techniques in face anonymization and recovery, while preserving high data utility. Code is available at https://github.com/Harxis/G2Face.
format Preprint
id arxiv_https___arxiv_org_abs_2408_09458
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle G2Face: High-Fidelity Reversible Face Anonymization via Generative and Geometric Priors
Yang, Haoxin
Xu, Xuemiao
Xu, Cheng
Zhang, Huaidong
Qin, Jing
Wang, Yi
Heng, Pheng-Ann
He, Shengfeng
Computer Vision and Pattern Recognition
Reversible face anonymization, unlike traditional face pixelization, seeks to replace sensitive identity information in facial images with synthesized alternatives, preserving privacy without sacrificing image clarity. Traditional methods, such as encoder-decoder networks, often result in significant loss of facial details due to their limited learning capacity. Additionally, relying on latent manipulation in pre-trained GANs can lead to changes in ID-irrelevant attributes, adversely affecting data utility due to GAN inversion inaccuracies. This paper introduces G\textsuperscript{2}Face, which leverages both generative and geometric priors to enhance identity manipulation, achieving high-quality reversible face anonymization without compromising data utility. We utilize a 3D face model to extract geometric information from the input face, integrating it with a pre-trained GAN-based decoder. This synergy of generative and geometric priors allows the decoder to produce realistic anonymized faces with consistent geometry. Moreover, multi-scale facial features are extracted from the original face and combined with the decoder using our novel identity-aware feature fusion blocks (IFF). This integration enables precise blending of the generated facial patterns with the original ID-irrelevant features, resulting in accurate identity manipulation. Extensive experiments demonstrate that our method outperforms existing state-of-the-art techniques in face anonymization and recovery, while preserving high data utility. Code is available at https://github.com/Harxis/G2Face.
title G2Face: High-Fidelity Reversible Face Anonymization via Generative and Geometric Priors
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.09458