CLR-Face: Conditional Latent Refinement for Blind Face Restoration Using Score-Based Diffusion Models

Recent generative-prior-based methods have shown promising blind face restoration performance. They usually project the degraded images to the latent space and then decode high-quality faces either by single-stage latent optimization or directly from the encoding. Generating fine-grained facial details faithful to inputs remains a challenging problem. Most existing methods produce either overly smooth outputs or alter the identity as they attempt to balance between generation and reconstruction. This may be attributed to the typical trade-off between quality and resolution in …

blind cs.cv decode diffusion diffusion models encoding face fine-grained generative images inputs optimization performance prior project quality space stage