Boosting Image Restoration via Priors from Pre-trained Models

arXiv:2403.06793v1 Announce Type: new
Abstract: Pre-trained models with large-scale training data, such as CLIP and Stable Diffusion, have demonstrated remarkable performance in various high-level computer vision tasks such as image understanding and generation from language descriptions. Yet, their potential for low-level tasks such as image restoration remains relatively unexplored. In this paper, we explore such models to enhance image restoration. As off-the-shelf features (OSF) from pre-trained models do not directly serve image restoration, we propose to learn an additional lightweight …

abstract arxiv boosting clip computer computer vision cs.cv data diffusion image image restoration language low paper performance pre-trained models scale stable diffusion tasks training training data type understanding via vision