Photo-Realistic Image Restoration in the Wild with Controlled Vision-Language Models

arXiv:2404.09732v1 Announce Type: new
Abstract: Though diffusion models have been successfully applied to various image restoration (IR) tasks, their performance is sensitive to the choice of training datasets. Typically, diffusion models trained in specific datasets fail to recover images that have out-of-distribution degradations. To address this problem, this work leverages a capable vision-language model and a synthetic degradation pipeline to learn image restoration in the wild (wild IR). More specifically, all low-quality images are simulated with a synthetic degradation pipeline …

abstract arxiv cs.cv datasets diffusion diffusion models distribution image image restoration images language language models performance photo tasks training training datasets type vision vision-language models work