English

DeepPrivacy2: Towards Realistic Full-Body Anonymization

Computer Vision and Pattern Recognition 2022-11-18 v1

Abstract

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.

Keywords

Cite

@article{arxiv.2211.09454,
  title  = {DeepPrivacy2: Towards Realistic Full-Body Anonymization},
  author = {Håkon Hukkelås and Frank Lindseth},
  journal= {arXiv preprint arXiv:2211.09454},
  year   = {2022}
}

Comments

Accepted at WACV2023

R2 v1 2026-06-28T06:06:35.382Z