The UU-Net: Reversible Face De-Identification for Visual Surveillance Video Footage

TL;DR

This paper introduces the UU-Net, a reversible face de-identification method for low-resolution video that generates realistic anonymized streams while retaining the ability to reconstruct original identities for security purposes.

Contribution

It presents a landmark-free, generative adversarial network-based approach that produces photo-realistic de-identified videos with controllable facial attributes, enabling reversible privacy protection.

Findings

Effective de-identification in low-resolution videos.

High-quality reconstruction of original scenes and identities.

Versatile control over facial attribute preservation.

Abstract

We propose a reversible face de-identification method for low resolution video data, where landmark-based techniques cannot be reliably used. Our solution is able to generate a photo realistic de-identified stream that meets the data protection regulations and can be publicly released under minimal privacy constraints. Notably, such stream encapsulates all the information required to later reconstruct the original scene, which is useful for scenarios, such as crime investigation, where the identification of the subjects is of most importance. We describe a learning process that jointly optimizes two main components: 1) a public module, that receives the raw data and generates the de-identified stream, where the ID information is surrogated in a photo-realistic and seamless way; and 2) a private module, designed for legal/security authorities, that analyses the public stream and reconstructs the original scene, disclosing the actual IDs of all the subjects in the scene. The proposed solution is landmarks-free and uses a conditional generative adversarial network to generate synthetic faces that preserve pose, lighting, background information and even facial expressions. Also, we enable full control over the set of soft facial attributes that should be preserved between the raw and de-identified data, which broads the range of applications for this solution. Our experiments were conducted in three different visual surveillance datasets (BIODI, MARS and P-DESTRE) and showed highly encouraging results. The source code is available at https://github.com/hugomcp/uu-net.