Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

Remove and recover: Deep end-to-end two-stage attention network for single-shot heavy rain removal

Authors
Ahn, Woo JinKang, Tae KooChoi, Hyun DuckLim, Myo Taeg
Issue Date
7-4월-2022
Publisher
ELSEVIER
Keywords
Image processing; Convolutional neural network; Image dehazing; Image deraining
Citation
NEUROCOMPUTING, v.481, pp.216 - 227
Indexed
SCIE
SCOPUS
Journal Title
NEUROCOMPUTING
Volume
481
Start Page
216
End Page
227
URI
https://scholar.korea.ac.kr/handle/2021.sw.korea/139321
DOI
10.1016/j.neucom.2022.01.041
ISSN
0925-2312
Abstract
In this paper, we propose a novel heavy rain removal algorithm using a deep neural network. Unlike most of the existing deraining methods, heavy rain removal is a more challenging task because it is necessary to remove both the rain marks and the haze effects, which are entangled in a complex manner. Motivated by this, we propose a new end-to-end two-stage attention network for single-shot heavy rain removal. The proposed network is connected serially with a removal network and a recovery network, which are based on a newly introduced dilation-wise attention block and skip attention block. Based on these attention techniques, the removal network predicts the heavy rain effect that needs to be removed from a given image, and the recovery network successfully predicts the details that need to be recovered, resulting in a clean image. We also introduce a new realistic RainCityscapes+ dataset, composed of synthesized outdoor images, and demonstrate extensive experiments, the results of which show our approach outperforms the state-of-the-art methods on both real and synthetic datasets quantitatively and qualitatively. (c) 2022 Elsevier B.V. All rights reserved.
Files in This Item
There are no files associated with this item.
Appears in
Collections
College of Engineering > School of Electrical Engineering > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher Lim, Myo taeg photo

Lim, Myo taeg
공과대학 (전기전자공학부)
Read more

Altmetrics

Total Views & Downloads

BROWSE