Improving Image De-raining Using Reference-Guided Transformers

TL;DR

This paper introduces a reference-guided transformer network that enhances image de-raining quality by refining results from existing methods using a clean reference image, validated across multiple datasets.

Contribution

The paper proposes a novel reference-guided transformer module that improves existing de-raining methods by leveraging a clean reference image for refinement.

Findings

Improves de-raining results across multiple datasets

Enhances existing CNN and transformer-based methods

Produces more visually pleasing de-rained images

Abstract

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 de-rained results. In this paper, we present a reference-guided de-raining filter, a transformer network that enhances de-raining 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, CNN-based, and transformer-based approaches.