无需提示词即可匿名化人脸，还能保留面部特征。
Reverse Personalization
- 用扩散模型反向生成，直接操控图像不依赖文本提示。
- 在未见过的人脸上仍能有效去身份，且保持表情等属性不变。
- 适合需要保护隐私又想保留面部细节的场景。
近期的文本到图像扩散模型已能根据文本提示和人像身份生成逼真面部图像，实现个性化图像生成。然而，现有基于提示的方法在移除或修改身份特征时，要么要求目标人物出现在预训练模型的训练数据中，要么需为特定身份微调模型。本文分析了身份生成过程，提出一种用于人脸匿名化的逆向个性化框架。该方法利用条件扩散反演，可在无需文本提示的情况下直接操作图像。为提升对模型训练数据外人物的泛化能力，引入身份引导的条件分支。与以往匿名方法不同，本框架支持可控的面部属性保留。实验表明，该方法在去身份效果、属性保留和图像质量之间达到当前最优平衡。源代码与数据已公开于 https://github.com/hanweikung/reverse-personalization。
原文摘要 · Abstract (English)
Recent text-to-image diffusion models have demonstrated remarkable generation of realistic facial images conditioned on textual prompts and human identities, enabling creating personalized facial imagery. However, existing prompt-based methods for removing or modifying identity-specific features rely either on the subject being well-represented in the pre-trained model or require model fine-tuning for specific identities. In this work, we analyze the identity generation process and introduce a reverse personalization framework for face anonymization. Our approach leverages conditional diffusion inversion, allowing direct manipulation of images without using text prompts. To generalize beyond subjects in the model's training data, we incorporate an identity-guided conditioning branch. Unlike prior anonymization methods, which lack control over facial attributes, our framework supports attribute-controllable anonymization. We demonstrate that our method achieves a state-of-the-art balance between identity removal, attribute preservation, and image quality. Source code and data are available at https://github.com/hanweikung/reverse-personalization .
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。