无需训练即可局部匿名化人脸，保护隐私同时保留表情等关键特征。
NullFace: Training-Free Localized Face Anonymization
- 利用预训练扩散模型反推图像噪声，通过修改身份嵌入实现匿名化。
- 在保持表情、姿态等非身份属性上优于现有方法，图像质量高。
- 支持局部匿名，适合需要精准控制隐私范围的场景。
随着摄像头数量激增，数字时代隐私问题日益突出。现有匿名化方法虽能隐藏身份信息，但常损害图像实用性。本文提出一种无需训练的面部匿名化方法，可保留关键非身份属性。该方法基于预训练文本到图像扩散模型，不需优化或训练。首先将输入图像反演为初始噪声，再通过身份条件扩散过程去噪，其中修改的身份嵌入确保匿名后人脸与原身份不同。该方法支持局部匿名，用户可自主选择需匿名的面部区域。全面评估显示，相比当前最优方法，本方法在匿名化效果、属性保留和图像质量方面均表现更优。其灵活性、鲁棒性与实用性使其适用于真实场景。代码与数据见：https://github.com/hanweikung/nullface。
原文摘要 · Abstract (English)
Privacy concerns around ever increasing number of cameras are increasing in today's digital age. Although existing anonymization methods are able to obscure identity information, they often struggle to preserve the utility of the images. In this work, we introduce a training-free method for face anonymization that preserves key non-identity-related attributes. Our approach utilizes a pre-trained text-to-image diffusion model without requiring optimization or training. It begins by inverting the input image to recover its initial noise. The noise is then denoised through an identity-conditioned diffusion process, where modified identity embeddings ensure the anonymized face is distinct from the original identity. Our approach also supports localized anonymization, giving users control over which facial regions are anonymized or kept intact. Comprehensive evaluations against state-of-the-art methods show our approach excels in anonymization, attribute preservation, and image quality. Its flexibility, robustness, and practicality make it well-suited for real-world applications. Code and data can be found at https://github.com/hanweikung/nullface .
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。