Prefer a chat interface with context about you and your work?
CLR-Face: Conditional Latent Refinement for Blind Face Restoration Using Score-Based Diffusion Models
Recent generative 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 challenging. Most existing methods produce either overly …