Zero-UMSIE:基于同构特征的零镜头水下多尺度图像增强方法。

IF 3.2 2区 物理与天体物理 Q2 OPTICS
Optics express Pub Date : 2024-11-04 DOI:10.1364/OE.538120
Tong Liu, Kaiyan Zhu, Weiye Cao, Bolin Shan, Fangyi Guo
{"title":"Zero-UMSIE:基于同构特征的零镜头水下多尺度图像增强方法。","authors":"Tong Liu, Kaiyan Zhu, Weiye Cao, Bolin Shan, Fangyi Guo","doi":"10.1364/OE.538120","DOIUrl":null,"url":null,"abstract":"<p><p>Due to the scattering and absorption of light, underwater images often exhibit degradation. Given the scarcity of paired real-world data and the inability of synthetic paired data to perfectly approximate real-world data, it's a challenge to restore these degraded images using deep neural networks. In this paper, a zero-shot underwater multi-scale image enhancement method (Zero-UMSIE) is proposed, which utilizes the isomorphism between the original underwater image and the re-degraded image. Specifically, Zero-UMSIE first estimates three latent components of the original underwater image: the global background light, the transmission map, and the scene radiance. Then, the estimated scene radiance is randomly mixed with the original underwater image to generate re-degraded images. Finally, a multi-scale loss and a set of tailored non-reference loss functions are employed to fine-tune the underwater image and enhance the generalization ability of the network. These functions implicitly control the learning preferences of the network and effectively address issues such as color bias and uneven illumination in underwater images, without the need for additional datasets. The proposed method is evaluated on three widely used real-world underwater image datasets. Extensive experiments on various benchmarks demonstrate that the proposed method is superior to state-of-the-art methods subjectively and objectively, which is competitive and applicable to diverse underwater conditions.</p>","PeriodicalId":19691,"journal":{"name":"Optics express","volume":"32 23","pages":"40398-40415"},"PeriodicalIF":3.2000,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Zero-UMSIE: a zero-shot underwater multi-scale image enhancement method based on isomorphic features.\",\"authors\":\"Tong Liu, Kaiyan Zhu, Weiye Cao, Bolin Shan, Fangyi Guo\",\"doi\":\"10.1364/OE.538120\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Due to the scattering and absorption of light, underwater images often exhibit degradation. Given the scarcity of paired real-world data and the inability of synthetic paired data to perfectly approximate real-world data, it's a challenge to restore these degraded images using deep neural networks. In this paper, a zero-shot underwater multi-scale image enhancement method (Zero-UMSIE) is proposed, which utilizes the isomorphism between the original underwater image and the re-degraded image. Specifically, Zero-UMSIE first estimates three latent components of the original underwater image: the global background light, the transmission map, and the scene radiance. Then, the estimated scene radiance is randomly mixed with the original underwater image to generate re-degraded images. Finally, a multi-scale loss and a set of tailored non-reference loss functions are employed to fine-tune the underwater image and enhance the generalization ability of the network. These functions implicitly control the learning preferences of the network and effectively address issues such as color bias and uneven illumination in underwater images, without the need for additional datasets. The proposed method is evaluated on three widely used real-world underwater image datasets. Extensive experiments on various benchmarks demonstrate that the proposed method is superior to state-of-the-art methods subjectively and objectively, which is competitive and applicable to diverse underwater conditions.</p>\",\"PeriodicalId\":19691,\"journal\":{\"name\":\"Optics express\",\"volume\":\"32 23\",\"pages\":\"40398-40415\"},\"PeriodicalIF\":3.2000,\"publicationDate\":\"2024-11-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Optics express\",\"FirstCategoryId\":\"101\",\"ListUrlMain\":\"https://doi.org/10.1364/OE.538120\",\"RegionNum\":2,\"RegionCategory\":\"物理与天体物理\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"OPTICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Optics express","FirstCategoryId":"101","ListUrlMain":"https://doi.org/10.1364/OE.538120","RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"OPTICS","Score":null,"Total":0}
引用次数: 0

摘要

由于光的散射和吸收,水下图像经常会出现衰减。鉴于配对真实世界数据的稀缺性,以及合成配对数据无法完美逼近真实世界数据,使用深度神经网络来修复这些劣化图像是一项挑战。本文提出了一种零镜头水下多尺度图像增强方法(Zero-UMSIE),该方法利用了原始水下图像和重新降级图像之间的同构性。具体来说,Zero-UMSIE 首先估计原始水下图像的三个潜在成分:全局背景光、透射图和场景辐射度。然后,将估算出的场景辐射度与原始水下图像随机混合,生成重新降级的图像。最后,采用多尺度损失和一组定制的非参考损失函数对水下图像进行微调,并增强网络的泛化能力。这些函数隐式地控制了网络的学习偏好,并有效地解决了水下图像中的颜色偏差和光照不均等问题,而无需额外的数据集。我们在三个广泛使用的真实世界水下图像数据集上对所提出的方法进行了评估。在各种基准上进行的广泛实验证明,所提出的方法在主观和客观上都优于最先进的方法,具有竞争力,适用于各种水下条件。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Zero-UMSIE: a zero-shot underwater multi-scale image enhancement method based on isomorphic features.

Due to the scattering and absorption of light, underwater images often exhibit degradation. Given the scarcity of paired real-world data and the inability of synthetic paired data to perfectly approximate real-world data, it's a challenge to restore these degraded images using deep neural networks. In this paper, a zero-shot underwater multi-scale image enhancement method (Zero-UMSIE) is proposed, which utilizes the isomorphism between the original underwater image and the re-degraded image. Specifically, Zero-UMSIE first estimates three latent components of the original underwater image: the global background light, the transmission map, and the scene radiance. Then, the estimated scene radiance is randomly mixed with the original underwater image to generate re-degraded images. Finally, a multi-scale loss and a set of tailored non-reference loss functions are employed to fine-tune the underwater image and enhance the generalization ability of the network. These functions implicitly control the learning preferences of the network and effectively address issues such as color bias and uneven illumination in underwater images, without the need for additional datasets. The proposed method is evaluated on three widely used real-world underwater image datasets. Extensive experiments on various benchmarks demonstrate that the proposed method is superior to state-of-the-art methods subjectively and objectively, which is competitive and applicable to diverse underwater conditions.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Optics express
Optics express 物理-光学
CiteScore
6.60
自引率
15.80%
发文量
5182
审稿时长
2.1 months
期刊介绍: Optics Express is the all-electronic, open access journal for optics providing rapid publication for peer-reviewed articles that emphasize scientific and technology innovations in all aspects of optics and photonics.
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信