A Utility-Preserving GAN for Face Obscuration
This addresses privacy concerns in applications like TV news and Google StreetView by providing a more secure alternative to traditional methods like blurring, though it is incremental as it builds on existing GAN techniques.
The paper tackles the problem of face obscuration for privacy protection by proposing UP-GAN, a generative model that effectively conceals identity while preserving non-identifying facial features like age and gender, achieving the best performance in both obscuration and utility preservation.
From TV news to Google StreetView, face obscuration has been used for privacy protection. Due to recent advances in the field of deep learning, obscuration methods such as Gaussian blurring and pixelation are not guaranteed to conceal identity. In this paper, we propose a utility-preserving generative model, UP-GAN, that is able to provide an effective face obscuration, while preserving facial utility. By utility-preserving we mean preserving facial features that do not reveal identity, such as age, gender, skin tone, pose, and expression. We show that the proposed method achieves the best performance in terms of obscuration and utility preservation.