Adversarial Context Aggregation Network for Low-Light Image Enhancement

Y. Shin, M. Sagong, Yoon-Jae Yeo, S. Ko
{"title":"Adversarial Context Aggregation Network for Low-Light Image Enhancement","authors":"Y. Shin, M. Sagong, Yoon-Jae Yeo, S. Ko","doi":"10.1109/DICTA.2018.8615848","DOIUrl":null,"url":null,"abstract":"Image captured in the low-light environments usually suffers from the low dynamic ranges and noise which degrade the quality of the image. Recently, convolutional neural network (CNN) has been employed for low-light image enhancement to simultaneously perform the brightness enhancement and noise removal. Although conventional CNN based techniques exhibit superior performance compared to traditional non-CNN based methods, they often produce the image with visual artifacts due to the small receptive field in their network. In order to cope with this problem, we propose an adversarial context aggregation network (ACA-net) for low-light image enhancement, which effectively aggregates the global context via full-resolution intermediate layers. In the proposed method, we first increase the brightness of a low-light image using the two different gamma correction functions and then feed the brightened images to CNN to obtain the enhanced image. To this end, we train ACA network using L1 pixel-wise reconstruction loss and adversarial loss which encourages the network to generate a natural image. Experimental results show that the proposed method achieves state-of-the-art results in terms of peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM).1","PeriodicalId":130057,"journal":{"name":"2018 Digital Image Computing: Techniques and Applications (DICTA)","volume":"93 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 Digital Image Computing: Techniques and Applications (DICTA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/DICTA.2018.8615848","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3

Abstract

Image captured in the low-light environments usually suffers from the low dynamic ranges and noise which degrade the quality of the image. Recently, convolutional neural network (CNN) has been employed for low-light image enhancement to simultaneously perform the brightness enhancement and noise removal. Although conventional CNN based techniques exhibit superior performance compared to traditional non-CNN based methods, they often produce the image with visual artifacts due to the small receptive field in their network. In order to cope with this problem, we propose an adversarial context aggregation network (ACA-net) for low-light image enhancement, which effectively aggregates the global context via full-resolution intermediate layers. In the proposed method, we first increase the brightness of a low-light image using the two different gamma correction functions and then feed the brightened images to CNN to obtain the enhanced image. To this end, we train ACA network using L1 pixel-wise reconstruction loss and adversarial loss which encourages the network to generate a natural image. Experimental results show that the proposed method achieves state-of-the-art results in terms of peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM).1
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
用于弱光图像增强的对抗上下文聚合网络
在弱光环境下拍摄的图像通常会受到低动态范围和噪声的影响,从而降低图像质量。近年来,卷积神经网络(convolutional neural network, CNN)被用于微光图像增强,在增强亮度的同时去噪。尽管传统的基于CNN的技术与传统的非基于CNN的方法相比表现出优越的性能,但由于其网络中的接受野较小,它们通常会产生带有视觉伪影的图像。为了解决这一问题,我们提出了一种对抗上下文聚合网络(ACA-net)用于弱光图像增强,该网络通过全分辨率中间层有效地聚合全局上下文。在本文提出的方法中,我们首先使用两种不同的伽玛校正函数增加低光图像的亮度,然后将增亮后的图像馈送给CNN,得到增强后的图像。为此,我们使用L1像素重建损失和对抗损失来训练ACA网络,这鼓励网络生成自然图像。实验结果表明,该方法在峰值信噪比(PSNR)和结构相似度指标(SSIM)方面均取得了较好的效果
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Satellite Multi-Vehicle Tracking under Inconsistent Detection Conditions by Bilevel K-Shortest Paths Optimization Classification of White Blood Cells using Bispectral Invariant Features of Nuclei Shape Impulse-Equivalent Sequences and Arrays Impact of MRI Protocols on Alzheimer's Disease Detection Strided U-Net Model: Retinal Vessels Segmentation using Dice Loss
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1