Paper Info
Title
Residual-Guide Network for Single Image Deraining.
Abstract
Single image rain streaks removal is extremely important since rainy condition adversely affects many computer vision systems. Deep learning based methods have 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 high-quality reconstruction while using fewer parameters than previous methods. Specifically, we propose a cascaded network and adopt residuals from shallower blocks to guide deeper blocks. We can obtain a coarse-to-fine estimation of negative residual as the blocks go deeper with this strategy. The outputs of different blocks are merged into the final reconstruction. We adopt recursive convolution to build each block and apply supervision to intermediate de-rained results. 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.
Year
DOI
Venue
2018
10.1145/3240508.3240694
MM '18: ACM Multimedia Conference Seoul Republic of Korea October, 2018
Field
DocType
ISBN
Computer vision,Residual,Feature fusion,Computer science,Vehicle detection,Recursive convolution,Artificial intelligence,Deep learning,Computational resource
Conference
978-1-4503-5665-7
Citations 
PageRank 
References 
13
0.58
19
Authors
5
Name
Order
Citations
PageRank
Zhiwen Fan1293.15
Huafeng Wu217421.31
Xueyang Fu335429.09
Yue Huang431729.82
Xinghao Ding559152.95