Exploiting Regional Information Transformer for Single Image Deraining

TL;DR

This paper introduces Regformer, a novel transformer-based approach for single image deraining that independently processes rain-affected and unaffected regions, leading to superior deraining performance by capturing detailed features and regional interactions.

Contribution

The paper proposes the Region Transformer (Regformer) with a Region Transformer Block (RTB) that uses Region Masked Attention and a Mixed Gate Forward Block to improve rain removal by separately handling different regions.

Findings

Achieves state-of-the-art deraining results

Effectively captures regional interactions and local details

Significantly improves image quality after deraining

Abstract

Transformer-based Single Image Deraining (SID) methods have achieved remarkable success, primarily attributed to their robust capability in capturing long-range interactions. However, we've noticed that current methods handle rain-affected and unaffected regions concurrently, overlooking the disparities between these areas, resulting in confusion between rain streaks and background parts, and inabilities to obtain effective interactions, ultimately resulting in suboptimal deraining outcomes. To address the above issue, we introduce the Region Transformer (Regformer), a novel SID method that underlines the importance of independently processing rain-affected and unaffected regions while considering their combined impact for high-quality image reconstruction. The crux of our method is the innovative Region Transformer Block (RTB), which integrates a Region Masked Attention (RMA) mechanism and a Mixed Gate Forward Block (MGFB). Our RTB is used for attention selection of rain-affected and unaffected regions and local modeling of mixed scales. The RMA generates attention maps tailored to these two regions and their interactions, enabling our model to capture comprehensive features essential for rain removal. To better recover high-frequency textures and capture more local details, we develop the MGFB as a compensation module to complete local mixed scale modeling. Extensive experiments demonstrate that our model reaches state-of-the-art performance, significantly improving the image deraining quality. Our code and trained models are publicly available.