DeepPrivacy2: Towards Realistic Full-Body Anonymization

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.

Cite

Text

Hukkelås and Lindseth. "DeepPrivacy2: Towards Realistic Full-Body Anonymization." Winter Conference on Applications of Computer Vision, 2023.

Markdown

[Hukkelås and Lindseth. "DeepPrivacy2: Towards Realistic Full-Body Anonymization." Winter Conference on Applications of Computer Vision, 2023.](https://mlanthology.org/wacv/2023/hukkelas2023wacv-deepprivacy2/)

BibTeX

@inproceedings{hukkelas2023wacv-deepprivacy2,
  title     = {{DeepPrivacy2: Towards Realistic Full-Body Anonymization}},
  author    = {Hukkelås, Håkon and Lindseth, Frank},
  booktitle = {Winter Conference on Applications of Computer Vision},
  year      = {2023},
  pages     = {1329-1338},
  url       = {https://mlanthology.org/wacv/2023/hukkelas2023wacv-deepprivacy2/}
}