SIA OpenIR  > 光电信息技术研究室
Non-local channel aggregation network for single image rain removal
Su, Zhipeng1; Zhang YX(张贻雄)1; Zhang, Xiao-Ping2; Qi F(祁峰)3
Department光电信息技术研究室
Source PublicationNeurocomputing
ISSN0925-2312
2022
Volume469Pages:261-272
Indexed BySCI ; EI
EI Accession number20214611150559
WOS IDWOS:000719323600008
Contribution Rank3
Funding OrganizationScience and Technology Key Project of Fujian Province (2019H6001, 2019HZ020009, 2020HZ020005, 2021HZ021004 and 2021H61010115) ; National Natural Science Foundation of China (Grant No. U1705263) ; President’s Fund of Xiamen University for Undergraduate (No. 20720212006) ; Open Project of Key Laboratory of Wireless Sensor Network & Communication, Shanghai Institute of Microsystem and Information Technology, CAS
KeywordNon-local channel aggregation Rain removal Neural network SIRR problem
Abstract

Rain streaks showing in images or videos would severely degrade the performance of computer vision applications. Thus, it is of vital importance to remove rain streaks and facilitate our vision systems. While recent convolutional neural network based methods have shown promising results in single image rain removal (SIRR), they fail to effectively capture long-range location dependencies or aggregate convolutional channel information simultaneously. However, as SIRR is a highly ill-posed problem, these spatial and channel information are very important clues to solve SIRR. First, spatial information could help our model to understand the image context by gathering long-range dependency location information hidden in the image. Second, aggregating channels could help our model to concentrate on channels more related to image background instead of rain streaks. In this paper, we propose a non-local channel aggregation network (NCANet) to address the SIRR problem. NCANet models 2D rainy images as sequences of vectors in three directions, namely vertical direction, transverse direction, and channel direction. Recurrently aggregating information from all three directions enables our model to capture the long-range dependencies in both channels and spatial locations. Extensive experiments on both heavy and light rain image data sets demonstrate the effectiveness of the proposed NCANet model.

Language英语
WOS SubjectComputer Science, Artificial Intelligence
WOS Research AreaComputer Science
Funding ProjectScience and Technology Key Project of Fujian Province[2019H6001] ; Science and Technology Key Project of Fujian Province[2019HZ020009] ; Science and Technology Key Project of Fujian Province[2020HZ020005] ; Science and Technology Key Project of Fujian Province[2021HZ021004] ; Science and Technology Key Project of Fujian Province[2021H61010115] ; National Natural Science Foundation of China[U1705263] ; President's Fund of Xiamen University for Under-graduate[20720212006] ; Open Project of Key Labora-tory of Wireless Sensor Network & Communication, Shanghai Institute of Microsystem and Information Technology, CAS
Citation statistics
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/29888
Collection光电信息技术研究室
Corresponding AuthorZhang YX(张贻雄)
Affiliation1.Department of Information Science and Engineering, Xiamen University, China
2.Department of Electrical Computer and Biomedical Engineering, Ryerson University, Toronto, ON, Canada
3.Shenyang Institute of Automation, Chinese Academy of Sciences, China
Recommended Citation
GB/T 7714
Su, Zhipeng,Zhang YX,Zhang, Xiao-Ping,et al. Non-local channel aggregation network for single image rain removal[J]. Neurocomputing,2022,469:261-272.
APA Su, Zhipeng,Zhang YX,Zhang, Xiao-Ping,&Qi F.(2022).Non-local channel aggregation network for single image rain removal.Neurocomputing,469,261-272.
MLA Su, Zhipeng,et al."Non-local channel aggregation network for single image rain removal".Neurocomputing 469(2022):261-272.
Files in This Item:
File Name/Size DocType Version Access License
Non-local channel ag(5132KB)期刊论文出版稿开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Su, Zhipeng]'s Articles
[Zhang YX(张贻雄)]'s Articles
[Zhang, Xiao-Ping]'s Articles
Baidu academic
Similar articles in Baidu academic
[Su, Zhipeng]'s Articles
[Zhang YX(张贻雄)]'s Articles
[Zhang, Xiao-Ping]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Su, Zhipeng]'s Articles
[Zhang YX(张贻雄)]'s Articles
[Zhang, Xiao-Ping]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Non-local channel aggregation network for single image rain removal.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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