Face Anonymity Based on Facial Pose Consistency

Abstract

With the development of artificial intelligence, there are more and more applications related to face images. The recording of face information causes potential cyber security risks and personal privacy disclosure risks to the public. To solve this problem, we hope to protect face privacy through face anonymity. This paper designs a conditional autoencoder that uses the data preprocessing method of image inpainting. Based on the realistic generation ability of StyleGAN, our autoencoder model introduces facial pose information as conditional information. The input image only contains pre-processed face-removed images. Our method can generate high-resolution images and maintain the posture of the original face. It can be used for identity-independent computer vision tasks. Experiments further proves the effectiveness of our anonymization framework.