Restoration by Generation with Constrained Priors

Input Anchor CodeFormer [56] Ours Figure 1 . We harness the generative capacity of a diffusion model for image restoration. By constraining the generative space with a generative or personal album, we can directly use a pre-trained diffusion model to produce a high-quality and realistic image that is also faithful to the input identity. Without any assumption on the degradation type, we are able to generalize to real-world images that exhibit complicated degradation. We compare our restoration result with CodeFormer, a state-of-the-art baseline [56] . Our method generalizes better to different types of degradation while more faithfully preserving the input identity. Images are best viewed zoomed in on a big screen.