Generative Personalized Blind Face Restoration Enhanced by Physical Identity

Facial image restoration plays an essential role in human-related restoration because faces carry significantly more identity information than other body parts. Furthermore, human perception is highly sensitive to facial disharmony, making face restoration critical for applications such as recognition, aesthetics, and overall visual experience. These factors distinguish face restoration from general image restoration tasks. Leveraging the powerful generative capabilities of diffusion models, we propose a robust blind face restoration system that integrates personalized information from personal albums, along with 3D facial geometry and fine-scale surface details derived from the degraded input’s physical identity. Our approach effectively addresses a variety of facial degradations, particularly in severely degraded cases where other blind face restoration methods often fail.