DeepPrivacy: A Generative Adversarial Network for Face Anonymization

TL;DR

DeepPrivacy introduces a GAN-based method that automatically anonymizes faces in images by generating realistic, privacy-safe faces that preserve the original image context, enabling safe data sharing and further model training.

Contribution

It presents a novel conditional GAN architecture for face anonymization that guarantees privacy while maintaining image realism and data distribution.

Findings

Successfully anonymizes faces with high realism

Preserves original image background and pose

Generates diverse, privacy-safe face images

Abstract

We propose a novel architecture which is able to automatically anonymize faces in images while retaining the original data distribution. We ensure total anonymization of all faces in an image by generating images exclusively on privacy-safe information. Our model is based on a conditional generative adversarial network, generating images considering the original pose and image background. The conditional information enables us to generate highly realistic faces with a seamless transition between the generated face and the existing background. Furthermore, we introduce a diverse dataset of human faces, including unconventional poses, occluded faces, and a vast variability in backgrounds. Finally, we present experimental results reflecting the capability of our model to anonymize images while preserving the data distribution, making the data suitable for further training of deep learning models. As far as we know, no other solution has been proposed that guarantees the anonymization of faces while generating realistic images.