DCSFN: Deep Cross-scale Fusion Network for Single Image Rain Removal

TL;DR

This paper introduces a novel deep neural network architecture that leverages cross-scale feature fusion and inner-scale connections to improve single image rain removal, outperforming existing methods.

Contribution

It proposes a multi-sub-network structure with cross-scale fusion via GRU and inner-scale connection blocks for enhanced rain removal performance.

Findings

Outperforms state-of-the-art rain removal methods on synthetic datasets.

Effective utilization of multi-scale features improves rain representation.

Demonstrates robustness on real-world rainy images.

Abstract

Rain removal is an important but challenging computer vision task as rain streaks can severely degrade the visibility of images that may make other visions or multimedia tasks fail to work. Previous works mainly focused on feature extraction and processing or neural network structure, while the current rain removal methods can already achieve remarkable results, training based on single network structure without considering the cross-scale relationship may cause information drop-out. In this paper, we explore the cross-scale manner between networks and inner-scale fusion operation to solve the image rain removal task. Specifically, to learn features with different scales, we propose a multi-sub-networks structure, where these sub-networks are fused via a crossscale manner by Gate Recurrent Unit to inner-learn and make full use of information at different scales in these sub-networks. Further, we design an inner-scale connection block to utilize the multi-scale information and features fusion way between different scales to improve rain representation ability and we introduce the dense block with skip connection to inner-connect these blocks. Experimental results on both synthetic and real-world datasets have demonstrated the superiority of our proposed method, which outperforms over the state-of-the-art methods. The source code will be available at https://supercong94.wixsite.com/supercong94.