简化的面部匿名化

Face Anonymization Made Simple

November 1, 2024

作者: Han-Wei Kung, Tuomas Varanka, Sanjay Saha, Terence Sim, Nicu Sebe

cs.AI

摘要

当前的人脸匿名化技术通常依赖于由人脸识别模型计算的身份丢失，这可能不准确且不可靠。此外，许多方法需要额外的数据，如面部标志和面具，来指导合成过程。相比之下，我们的方法使用仅具有重建损失的扩散模型，消除了对面部标志或面具的需求，同时仍能生成具有复杂、细致细节的图像。我们通过定量和定性评估在两个公共基准上验证了我们的结果。我们的模型在三个关键领域取得了最先进的性能：身份匿名化、面部属性保留和图像质量。除了其主要的匿名化功能外，我们的模型还可以通过将额外的面部图像作为输入来执行人脸交换任务，展示了其多功能性和多样化应用的潜力。我们的代码和模型可在 https://github.com/hanweikung/face_anon_simple 获取。

English

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 .