DeepPrivacy2: Towards Realistic Full-Body Anonymization

Generative Adversarial Networks (GANs) are widely adopted for anonymization of human figures. However, current state-of-the-art limits anonymization to the task of face anonymization. In this paper, we propose a novel anonymization framework (DeepPrivacy2) for realistic anonymization of human figure...

Full description

Saved in:
Bibliographic Details
Main Authors: Hukkelas, Hakon, Lindseth, Frank
Format: Conference Proceeding
Language:English
Subjects:
accountable
Applications: Social good
Computational modeling
Computational photography
Computer vision
Data privacy
Deepfakes
ethical computer vision
Explainable
fair
Generative adversarial networks
image and video synthesis
Image quality
Privacy
privacy-preserving
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Generative Adversarial Networks (GANs) are widely adopted for anonymization of human figures. However, current state-of-the-art limits 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 full-body 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. Source code and appendix is available at: github.com/hukkelas/deep_privacy2.
ISSN:2642-9381
DOI:10.1109/WACV56688.2023.00138