Improving Image De-Raining Using Reference-Guided Transformers

Abstract

Translate Article

Image de-raining is a critical task in computer vision to improve visibility and enhance the robustness of outdoor vision systems. While recent advances in de-raining methods have achieved remarkable performance, the challenge remains to produce high-quality and visually pleasing derained results. In this paper, we present a reference-guided de-raining filter, a transformer network that enhances deraining results using a reference clean image as guidance. We leverage the capabilities of the proposed module to further refine the images de-rained by existing methods. We validate our method on three datasets and show that our module can improve the performance of existing prior-based, CNNbased, and transformer-based approaches.