arrow
返回

Exploring Overcomplete Representations for Single Image Deraining Using CNNs

delete2021-02-01
delete24
delete
OA
AI
R
Rajeev Yasarla *
J
Jeya Maria Jose Valanarasu
V
Vishal M. Patel
DOI:10.1109/JSTSP.2020.3039393delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
Removal of rain streaks from a single image is an extremely challenging problem since the rainy images often contain rain streaks of different size, shape, direction and density. Most recent methods for deraining use a deep network following a generic encoder-decoder architecture which captures low-level features across the initial layers and high-level features in the deeper layers. For the task of deraining, the rain streaks which are to be removed are relatively small and focusing much on global features is not an efficient way to solve the problem. To this end, in this article, we propose using an overcomplete convolutional network architecture which gives special attention in learning local structures by restraining the receptive field of filters. We combine it with U-Net so that it does not lose out on the global structures as well while focusing more on low-level features, to compute the derained image. The proposed network called, over-and-under complete deraining network (OUCD), consists of two branches: overcomplete branch which is confined to small receptive field size in order to focus on the local structures and an undercomplete branch that has larger receptive fields to primarily focus on global structures. Extensive experiments on synthetic and real datasets demonstrate that the proposed method achieves significant improvements over the recent state-of-the-art methods. Code is available at https://github.com/jeya-maria-jose/Derain_OUCD_Net
Keyword:
Rain
Task analysis
Network architecture
Feature extraction
Computer architecture
Convolutional codes
Convolution
Deep networks
deraining
overcomplete representations
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

IEEE Journal of Selected Topics in Signal Processing 封面图
IEEE Journal of Selected Topics in Signal Processing
IF:
13.7
论文数:
1.9K
被引数:
1.1W

机构

J
Johns Hopkins University
学者数:
10.2W
论文数: 8.8W
被引数: 13.0W
引用论文

引用论文

Electrochemically assisted micro localized grafting of aptamers in a microchannel engraved in fluorinated thermoplastic polymer Dyneon THV
err2015-01-01
err0
PREAI
errC. Perréard; Y. Ladner; F. d'Orlyé; S. Descroix; V. Taniga; A. Varenne; F. Kanoufi; C. Slim; S. Griveau; F. Bedioui
err分享
err收藏
Lightweight Pyramid Networks for Image Deraining
err2020-06-01
err294
errOAAI
errFu, Xueyang; Liang, Borong; Huang, Yue; Ding, Xinghao; Paisley, John
err分享
err收藏
Genomewide association study for C-reactive protein in Indians replicates known associations of common variants
err2019-02-26
err0
PREAI
errGauri Prasad; Anil K. Giri; Analabha Basu; Nikhil Tandon; Dwaipayan Bharadwaj
err分享
err收藏
err分享
err收藏
err分享
err收藏
A Hierarchical Approach for Rain or Snow Removing in a Single Color Image
err2017-08-01
err166
PREAI
errWang, Yinglong; Liu, Shuaicheng; Chen, Chen; Zeng, Bing
err分享
err收藏
学者 查看更多内容