Natural and Effective Obfuscation by Head Inpainting

TL;DR

This paper introduces a novel head inpainting method for privacy protection in social media photos, generating realistic obfuscated faces that outperform traditional blurring against recognition systems.

Contribution

The work presents a new head inpainting technique that combines facial landmark prediction from context with landmark-conditioned inpainting, improving realism and obfuscation effectiveness.

Findings

Generated head inpaintings are realistic and diverse.

Obfuscation outperforms traditional blurring against recognition.

Method effectively handles diverse activities and head orientations.

Abstract

As more and more personal photos are shared online, being able to obfuscate identities in such photos is becoming a necessity for privacy protection. People have largely resorted to blacking out or blurring head regions, but they result in poor user experience while being surprisingly ineffective against state of the art person recognizers. In this work, we propose a novel head inpainting obfuscation technique. Generating a realistic head inpainting in social media photos is challenging because subjects appear in diverse activities and head orientations. We thus split the task into two sub-tasks: (1) facial landmark generation from image context (e.g. body pose) for seamless hypothesis of sensible head pose, and (2) facial landmark conditioned head inpainting. We verify that our inpainting method generates realistic person images, while achieving superior obfuscation performance against automatic person recognizers.