My Body My Choice: Human-Centric Full-Body Anonymization

TL;DR

This paper introduces a human-guided full-body anonymization method called 'My Body My Choice' that offers adaptable privacy solutions through removal and swapping techniques, evaluated across multiple datasets and metrics.

Contribution

It presents a novel, flexible anonymization framework combining diffusion models and GANs, enabling context-aware human-centric privacy protection.

Findings

Outperforms state-of-the-art inpainting and anonymization methods

Effective in diverse cultural and security contexts

Reduces reidentification risk significantly

Abstract

In an era of increasing privacy concerns for our online presence, we propose that the decision to appear in a piece of content should only belong to the owner of the body. Although some automatic approaches for full-body anonymization have been proposed, human-guided anonymization can adapt to various contexts, such as cultural norms, personal relations, esthetic concerns, and security issues. ''My Body My Choice'' (MBMC) enables physical and adversarial anonymization by removal and swapping approaches aimed for four tasks, designed by single or multi, ControlNet or GAN modules, combining several diffusion models. We evaluate anonymization on seven datasets; compare with SOTA inpainting and anonymization methods; evaluate by image, adversarial, and generative metrics; and conduct reidentification experiments.