Towards Effective Multiple-in-One Image Restoration: A Sequential and Prompt Learning Strategy

arXiv:2401.03379v2 Announce Type: replace
Abstract: While single task image restoration (IR) has achieved significant successes, it remains a challenging issue to train a single model which can tackle multiple IR tasks. In this work, we investigate in-depth the multiple-in-one (MiO) IR problem, which comprises seven popular IR tasks. We point out that MiO IR faces two pivotal challenges: the optimization of diverse objectives and the adaptation to multiple tasks. To tackle these challenges, we present two simple yet effective strategies. …

abstract arxiv cs.cv image image restoration issue multiple popular prompt prompt learning strategy tasks train type work