OPT OpenIR  > 光谱成像技术研究室
Attention-Based Multi-Branch Network for Low-Light Image Enhancement
Jiao, Yin1,2; Zheng, Xiangtao2; Lu, Xiaoqiang2
2021-03-26
会议名称2nd IEEE International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering, ICBAIE 2021
会议录名称2021 IEEE 2nd International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering, ICBAIE 2021
页码401-407
会议日期2021-03-26
会议地点Nanchang, China
出版者Institute of Electrical and Electronics Engineers Inc.
产权排序1
摘要

Low-light conditions make the obtained images suffer a series of degradation, such as low contrast, noise interference and color distortion. Many previous learning-based methods have made remarkable progress, but they may still produce unsatisfactory results for ignoring noise in low-light regions. An attention-based multi-branch network is proposed, which can adequately enhance the image and suppress latent noise. The proposed method firstly estimates illumination component and reflectance component through a decomposition process. Then the illumination component is brightened to reconstruct the global lighting distribution, and the reflectance component is restored to remove noise and maintain details. A lightweight but effective attention block is employed to guide the restoration of the reflectance component, so as to concentrate on the distribution of lighting in different regions and effectively suppress noise in the dim environment. Extensive experiments on several datasets show the proposed method can achieve good results compared with classic and state-of-the-art methods. © 2021 IEEE.

关键词low-light enhancement multi-branch network retinex theory attention
作者部门光谱成像技术研究室
收录类别EI
ISBN号9780738131221
语种英语
EI入藏号20211710245631
文献类型会议论文
条目标识符http://ir.opt.ac.cn/handle/181661/94689
专题光谱成像技术研究室
作者单位1.University of Chinese Academy of Sciences, Beijing, China
2.Xi'an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Key Laboratory of Spectral Imaging Technology Cas, Xi'an, China
推荐引用方式
GB/T 7714
Jiao, Yin,Zheng, Xiangtao,Lu, Xiaoqiang. Attention-Based Multi-Branch Network for Low-Light Image Enhancement[C]:Institute of Electrical and Electronics Engineers Inc.,2021:401-407.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Attention-Based Mult(1348KB)会议论文 限制开放CC BY-NC-SA请求全文
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Jiao, Yin]的文章
[Zheng, Xiangtao]的文章
[Lu, Xiaoqiang]的文章
百度学术
百度学术中相似的文章
[Jiao, Yin]的文章
[Zheng, Xiangtao]的文章
[Lu, Xiaoqiang]的文章
必应学术
必应学术中相似的文章
[Jiao, Yin]的文章
[Zheng, Xiangtao]的文章
[Lu, Xiaoqiang]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。