NullFace：無需訓練的局部人臉匿名化技術

NullFace: Training-Free Localized Face Anonymization

March 11, 2025

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

cs.AI

摘要

在當今數位時代，隨著攝像頭數量的不斷增加，隱私問題日益受到關注。儘管現有的匿名化方法能夠隱藏身份信息，但它們往往難以保持圖像的實用性。在本研究中，我們提出了一種無需訓練的面部匿名化方法，該方法能夠保留關鍵的非身份相關屬性。我們的方法利用預訓練的文本到圖像擴散模型，無需進行優化或訓練。首先，通過反轉輸入圖像來恢復其初始噪聲。然後，通過身份條件擴散過程對噪聲進行去噪，其中修改後的身份嵌入確保匿名化面部與原始身份不同。我們的方法還支持局部匿名化，讓用戶能夠控制哪些面部區域被匿名化或保持原樣。與最先進方法的全面評估顯示，我們的方法在匿名化、屬性保留和圖像質量方面表現優異。其靈活性、魯棒性和實用性使其非常適合實際應用。代碼和數據可在 https://github.com/hanweikung/nullface 找到。

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 .