Multi-Scale Hourglass Hierarchical Fusion Network for Single Image Deraining

TL;DR

This paper introduces MH2F-Net, a novel multi-scale hierarchical network for single image deraining that effectively captures rain features and enhances image clarity through hierarchical feature fusion and attention mechanisms.

Contribution

The paper proposes a new multi-scale hourglass hierarchical fusion network with novel extraction and distillation blocks for improved rain removal in images.

Findings

Outperforms recent state-of-the-art deraining methods on synthetic datasets.

Effectively handles rain streaks of varying size, direction, and density.

Demonstrates robustness on real rainy images.

Abstract

Rain streaks bring serious blurring and visual quality degradation, which often vary in size, direction and density. Current CNN-based methods achieve encouraging performance, while are limited to depict rain characteristics and recover image details in the poor visibility environment. To address these issues, we present a Multi-scale Hourglass Hierarchical Fusion Network (MH2F-Net) in end-to-end manner, to exactly captures rain streak features with multi-scale extraction, hierarchical distillation and information aggregation. For better extracting the features, a novel Multi-scale Hourglass Extraction Block (MHEB) is proposed to get local and global features across different scales through down- and up-sample process. Besides, a Hierarchical Attentive Distillation Block (HADB) then employs the dual attention feature responses to adaptively recalibrate the hierarchical features and eliminate the redundant ones. Further, we introduce a Residual Projected Feature Fusion (RPFF) strategy to progressively discriminate feature learning and aggregate different features instead of directly concatenating or adding. Extensive experiments on both synthetic and real rainy datasets demonstrate the effectiveness of the designed MH2F-Net by comparing with recent state-of-the-art deraining algorithms. Our source code will be available on the GitHub: https://github.com/cxtalk/MH2F-Net.