Face Anonymization Made Simple

TL;DR

This paper introduces a simple face anonymization method using diffusion models that avoids reliance on facial landmarks or masks, achieving state-of-the-art results in identity anonymization, attribute preservation, and image quality.

Contribution

The proposed approach simplifies face anonymization by eliminating the need for auxiliary data and achieves superior performance with a diffusion model trained solely on reconstruction loss.

Findings

State-of-the-art anonymization performance

Effective facial attribute preservation

Versatility in face swapping tasks

Abstract

Current face anonymization techniques often depend on identity loss calculated by face recognition models, which can be inaccurate and unreliable. Additionally, many methods require supplementary data such as facial landmarks and masks to guide the synthesis process. In contrast, our approach uses diffusion models with only a reconstruction loss, eliminating the need for facial landmarks or masks while still producing images with intricate, fine-grained details. We validated our results on two public benchmarks through both quantitative and qualitative evaluations. Our model achieves state-of-the-art performance in three key areas: identity anonymization, facial attribute preservation, and image quality. Beyond its primary function of anonymization, our model can also perform face swapping tasks by incorporating an additional facial image as input, demonstrating its versatility and potential for diverse applications. Our code and models are available at https://github.com/hanweikung/face_anon_simple .