NullFace: Training-Free Localized Face Anonymization
This addresses privacy concerns for individuals in surveillance and digital media by offering a flexible and practical solution, though it is incremental as it builds on existing diffusion models.
The paper tackles the problem of face anonymization that preserves non-identity attributes by introducing a training-free method using a pre-trained diffusion model, achieving strong performance in anonymization, attribute preservation, and image quality compared to state-of-the-art methods.
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 .