A Hybrid Model for Identity Obfuscation by Face Replacement

TL;DR

This paper introduces a hybrid face replacement model that combines parametric face synthesis and GANs to effectively obfuscate identities in photos while maintaining realism and scene consistency.

Contribution

A novel hybrid approach integrating parametric face control with GAN-based synthesis for improved identity obfuscation in images.

Findings

Achieves higher obfuscation rates than previous methods.

Produces highly realistic face replacements.

Maintains better scene and content similarity.

Abstract

As more and more personal photos are shared and tagged in social media, avoiding privacy risks such as unintended recognition becomes increasingly challenging. We propose a new hybrid approach to obfuscate identities in photos by head replacement. Our approach combines state of the art parametric face synthesis with latest advances in Generative Adversarial Networks (GAN) for data-driven image synthesis. On the one hand, the parametric part of our method gives us control over the facial parameters and allows for explicit manipulation of the identity. On the other hand, the data-driven aspects allow for adding fine details and overall realism as well as seamless blending into the scene context. In our experiments, we show highly realistic output of our system that improves over the previous state of the art in obfuscation rate while preserving a higher similarity to the original image content.