Residual-Guide Feature Fusion Network for Single Image Deraining

TL;DR

ResGuideNet is a novel deep learning architecture for single image deraining that uses residual-guided feature fusion, achieving high-quality results efficiently and adaptable to various rainy conditions.

Contribution

The paper introduces ResGuideNet, a cascaded residual-guided feature fusion network with recursive convolution and multi-level supervision for improved image deraining.

Findings

Achieves promising performance on synthetic and real data.

Uses fewer parameters than previous methods.

Flexible to different rainy conditions.

Abstract

Single image rain streaks removal is extremely important since rainy images adversely affect many computer vision systems. Deep learning based methods have found great success in image deraining tasks. In this paper, we propose a novel residual-guide feature fusion network, called ResGuideNet, for single image deraining that progressively predicts highquality reconstruction. Specifically, we propose a cascaded network and adopt residuals generated from shallower blocks to guide deeper blocks. By using this strategy, we can obtain a coarse to fine estimation of negative residual as the blocks go deeper. The outputs of different blocks are merged into the final reconstruction. We adopt recursive convolution to build each block and apply supervision to all intermediate results, which enable our model to achieve promising performance on synthetic and real-world data while using fewer parameters than previous required. ResGuideNet is detachable to meet different rainy conditions. For images with light rain streaks and limited computational resource at test time, we can obtain a decent performance even with several building blocks. Experiments validate that ResGuideNet can benefit other low- and high-level vision tasks.