Multi-Scale Progressive Fusion Network for Single Image Deraining

TL;DR

This paper introduces a multi-scale progressive fusion network that leverages multi-resolution information and attention mechanisms to effectively remove rain streaks from single images, achieving state-of-the-art results.

Contribution

The proposed MSPFN uniquely combines multi-scale pyramid structures, attention-guided fusion, and recurrent global texture modeling for superior rain streak removal.

Findings

Achieves state-of-the-art performance on benchmark datasets.

Effective in joint deraining, detection, and segmentation tasks.

Promotes a new research direction in vision task-driven image deraining.

Abstract

Rain streaks in the air appear in various blurring degrees and resolutions due to different distances from their positions to the camera. Similar rain patterns are visible in a rain image as well as its multi-scale (or multi-resolution) versions, which makes it possible to exploit such complementary information for rain streak representation. In this work, we explore the multi-scale collaborative representation for rain streaks from the perspective of input image scales and hierarchical deep features in a unified framework, termed multi-scale progressive fusion network (MSPFN) for single image rain streak removal. For similar rain streaks at different positions, we employ recurrent calculation to capture the global texture, thus allowing to explore the complementary and redundant information at the spatial dimension to characterize target rain streaks. Besides, we construct multi-scale pyramid structure, and further introduce the attention mechanism to guide the fine fusion of this correlated information from different scales. This multi-scale progressive fusion strategy not only promotes the cooperative representation, but also boosts the end-to-end training. Our proposed method is extensively evaluated on several benchmark datasets and achieves state-of-the-art results. Moreover, we conduct experiments on joint deraining, detection, and segmentation tasks, and inspire a new research direction of vision task-driven image deraining. The source code is available at \url{https://github.com/kuihua/MSPFN}.