Photo-Realistic Image Restoration in the Wild with Controlled Vision-Language Models
This addresses the challenge of robust image restoration in the wild for applications like photography and media, though it is incremental as it builds upon existing diffusion models.
The paper tackles the problem of image restoration for out-of-distribution degradations by leveraging a vision-language model and synthetic degradation pipeline, achieving improved performance on both synthetic and real-world datasets with a fast posterior sampling strategy.
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 that contains multiple common degradations such as blur, resize, noise, and JPEG compression. Then we introduce robust training for a degradation-aware CLIP model to extract enriched image content features to assist high-quality image restoration. Our base diffusion model is the image restoration SDE (IR-SDE). Built upon it, we further present a posterior sampling strategy for fast noise-free image generation. We evaluate our model on both synthetic and real-world degradation datasets. Moreover, experiments on the unified image restoration task illustrate that the proposed posterior sampling improves image generation quality for various degradations.