Dual-Path Multi-Scale Transformer for High-Quality Image Deraining

TL;DR

This paper introduces DPMformer, a dual-path multi-scale Transformer that effectively leverages multi-scale features for high-quality image deraining, outperforming existing methods on benchmark datasets.

Contribution

The paper proposes a novel dual-path multi-scale Transformer architecture that combines coarse-to-fine and multi-patch strategies for improved rain removal.

Findings

Achieves superior performance on benchmark datasets.

Effectively captures multi-scale rain features.

Outperforms state-of-the-art deraining methods.

Abstract

Despite the superiority of convolutional neural networks (CNNs) and Transformers in single-image rain removal, current multi-scale models still face significant challenges due to their reliance on single-scale feature pyramid patterns. In this paper, we propose an effective rain removal method, the dual-path multi-scale Transformer (DPMformer) for high-quality image reconstruction by leveraging rich multi-scale information. This method consists of a backbone path and two branch paths from two different multi-scale approaches. Specifically, one path adopts the coarse-to-fine strategy, progressively downsampling the image to 1/2 and 1/4 scales, which helps capture fine-scale potential rain information fusion. Simultaneously, we employ the multi-patch stacked model (non-overlapping blocks of size 2 and 4) to enrich the feature information of the deep network in the other path. To learn a richer blend of features, the backbone path fully utilizes the multi-scale information to achieve high-quality rain removal image reconstruction. Extensive experiments on benchmark datasets demonstrate that our method achieves promising performance compared to other state-of-the-art methods.