DeepPrivacy2: Towards Realistic Full-Body Anonymization
It addresses privacy concerns for individuals in images by extending anonymization beyond faces to full bodies, though it is incremental as it builds on existing GAN-based approaches.
The paper tackles the problem of full-body anonymization of human figures, proposing DeepPrivacy2, a framework that uses a style-based GAN and a new large dataset to achieve realistic anonymization with stronger privacy guarantees than prior methods.
Generative Adversarial Networks (GANs) are widely adapted for anonymization of human figures. However, current state-of-the-art limit anonymization to the task of face anonymization. In this paper, we propose a novel anonymization framework (DeepPrivacy2) for realistic anonymization of human figures and faces. We introduce a new large and diverse dataset for human figure synthesis, which significantly improves image quality and diversity of generated images. Furthermore, we propose a style-based GAN that produces high quality, diverse and editable anonymizations. We demonstrate that our full-body anonymization framework provides stronger privacy guarantees than previously proposed methods.