G2Face: High-Fidelity Reversible Face Anonymization via generative and geometric priors

• Main Authors: YANG, Haoxin, XU, Xuemiao, XU, Cheng, ZHANG, Huaidong, QIN, Jing, WANG, Yi, HENG, Pheng-Ann, Shengfeng HE
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Data privacy; Face recognition; Faces; Feature extraction; Generative adversarial networks; generative prior; geometric prior; identity-aware feature fusion; Information filtering; Information integrity; Reversible face anonymization; Graphics and Human Computer Interfaces; Information Security
• Online Access: https://ink.library.smu.edu.sg/sis_research/9273; https://ink.library.smu.edu.sg/context/sis_research/article/10273/viewcontent/G2Face_av.pdf
• Institution: Singapore Management University

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 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.