AdaIR: Exploiting Underlying Similarities of Image Restoration Tasks with Adapters

arXiv:2404.11475v1 Announce Type: new
Abstract: Existing image restoration approaches typically employ extensive networks specifically trained for designated degradations. Despite being effective, such methods inevitably entail considerable storage costs and computational overheads due to the reliance on task-specific networks. In this work, we go beyond this well-established framework and exploit the inherent commonalities among image restoration tasks. The primary objective is to identify components that are shareable across restoration tasks and augment the shared components with modules specifically trained for individual …

abstract arxiv beyond computational costs cs.ai cs.cv exploit framework image image restoration networks reliance restoration storage storage costs tasks type work