Content-illumination coupling guided low-light image enhancement network | |
Zhao, Ruini1; Xie, Meilin1,4; Feng, Xubin1; Su, Xiuqin1,4![]() | |
作者部门 | 光电跟踪与测量技术研究室 |
2024-04-11 | |
发表期刊 | SCIENTIFIC REPORTS
![]() |
ISSN | 2045-2322 |
卷号 | 14期号:1 |
产权排序 | 1 |
摘要 | Current low-light enhancement algorithms fail to suppress noise when enhancing brightness, and may introduces structural distortion and color distortion caused by halos or artifacts. This paper proposes a content-illumination coupling guided low-light image enhancement network (CICGNet), it develops a truss topology based on Retinex as backbone to decompose low-light image component in an end-to-end way. The preservation of content features and the enhancement of illumination features are carried out along with depth and width direction of the truss topology. Each submodule uses the same resolution input and output to avoid the introduction of noise. Illumination component prevents misestimation of global and local illumination by using pre- and post-activation features at different depth levels, this way could avoid possible halos and artifacts. The network progressively enhances the illumination component and maintains the content component stage-by-stage. The proposed algorithm demonstrates better performance compared with advanced attention-based low-light enhancement algorithms and state-of-the-art image restoration algorithms. We also perform extensive ablation studies and demonstrate the impact of low-light enhancement algorithm on the downstream task of computer vision. Code is available at: https://github.com/Ruini94/CICGNet. |
关键词 | Low-light enhancement Retinex End-to-end Truss topology Pre- and post-activation |
DOI | 10.1038/s41598-024-58965-0 |
收录类别 | SCI |
语种 | 英语 |
WOS记录号 | WOS:001201413300037 |
出版者 | NATURE PORTFOLIO |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.opt.ac.cn/handle/181661/97426 |
专题 | 光电跟踪与测量技术研究室 |
通讯作者 | Feng, Xubin |
作者单位 | 1.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Key Lab Space Precis Measurement Technol, Xian 710119, Peoples R China 2.Shandong Prov Commun Planning & Design Inst Grp Co, Inst Intelligent Transportat, Jinan 250101, Peoples R China 3.Changan Univ, Xian 710064, Peoples R China 4.Pilot Natl Lab Marine Sci & Technol, Qingdao 266200, Peoples R China |
推荐引用方式 GB/T 7714 | Zhao, Ruini,Xie, Meilin,Feng, Xubin,et al. Content-illumination coupling guided low-light image enhancement network[J]. SCIENTIFIC REPORTS,2024,14(1). |
APA | Zhao, Ruini,Xie, Meilin,Feng, Xubin,Su, Xiuqin,Zhang, Huiming,&Yang, Wei.(2024).Content-illumination coupling guided low-light image enhancement network.SCIENTIFIC REPORTS,14(1). |
MLA | Zhao, Ruini,et al."Content-illumination coupling guided low-light image enhancement network".SCIENTIFIC REPORTS 14.1(2024). |
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 | ||
Content-illumination(8638KB) | 期刊论文 | 出版稿 | 限制开放 | CC BY-NC-SA | 请求全文 |
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。
修改评论