Face Anonymization Made Simple
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 .
Code (1)
Tasks
AttributeFace AnonymizationFace RecognitionFace SwappingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Secure and reversible face anonymization with diffusion models
Face anonymization aims to protect sensitive identity information by altering faces while preserving visual realism and utility for downstream computer vision tasks. Current methods struggle to simultaneously ensure high…
Face AnonymizationPassword-conditioned Anonymization and Deanonymization with Face Identity Transformers
Cameras are prevalent in our daily lives, and enable many useful systems built upon computer vision technologies such as smart cameras and home robots for service applications. However, there is also an increasing societ…
Multi-Task LearningPassword-conditioned Anonymization and Deanonymization with Face Identity Transformers
Cameras are prevalent in our daily lives, and enable many useful systems built upon computer vision technologies such as smart cameras and home robots for service applications. However, there is also an increasing societ…
Temporally coherent video anonymization through GAN inpainting
This work tackles the problem of temporally coherent face anonymization in natural video streams.We propose JaGAN, a two-stage system starting with detecting and masking out faces with black image patches in all individu…
Face AnonymizationGenerative Adversarial NetworkPrivacy PreservingDeepPrivacy2: Towards Realistic Full-Body Anonymization
Generative Adversarial Networks (GANs) are widely adapted for anonymization of human figures. However, current state-of-the-art limit anonymization to the task of face anonymization. In this paper, we propose a novel ano…
DiversityFace AnonymizationFull-body anonymization