CIAGAN: Conditional Identity Anonymization Generative Adversarial Networks

TL;DR

CIAGAN is a novel generative adversarial network model that effectively anonymizes faces and bodies in images and videos, balancing privacy protection with high-quality visual output for computer vision applications.

Contribution

The paper introduces CIAGAN, a conditional GAN framework that provides controlled and diverse anonymization of visual data, outperforming existing methods in privacy preservation and image quality.

Findings

Achieves state-of-the-art anonymization performance.

Maintains high visual quality of anonymized images and videos.

Provides full control over the de-identification process.

Abstract

The unprecedented increase in the usage of computer vision technology in society goes hand in hand with an increased concern in data privacy. In many real-world scenarios like people tracking or action recognition, it is important to be able to process the data while taking careful consideration in protecting people's identity. We propose and develop CIAGAN, a model for image and video anonymization based on conditional generative adversarial networks. Our model is able to remove the identifying characteristics of faces and bodies while producing high-quality images and videos that can be used for any computer vision task, such as detection or tracking. Unlike previous methods, we have full control over the de-identification (anonymization) procedure, ensuring both anonymization as well as diversity. We compare our method to several baselines and achieve state-of-the-art results.