Unsupervised Low-Light Image Enhancement via Luminance Mask and Luminance-Independent Representation Decoupling

IF 5.3 3区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

IEEE Transactions on Emerging Topics in Computational Intelligence Pub Date : 2024-03-14 DOI:10.1109/TETCI.2024.3369858

Bo Peng;Jia Zhang;Zhe Zhang;Qingming Huang;Liqun Chen;Jianjun Lei

{"title":"Unsupervised Low-Light Image Enhancement via Luminance Mask and Luminance-Independent Representation Decoupling","authors":"Bo Peng;Jia Zhang;Zhe Zhang;Qingming Huang;Liqun Chen;Jianjun Lei","doi":"10.1109/TETCI.2024.3369858","DOIUrl":null,"url":null,"abstract":"Enhancing low-light images in an unsupervised manner has become a popular topic due to the challenge of obtaining paired real-world low/normal-light images. Driven by massive available normal-light images, learning a low-light image enhancement network from unpaired data is more practical and valuable. This paper presents an unsupervised low-light image enhancement method (DeULLE) via luminance mask and luminance-independent representation decoupling based on unpaired data. Specifically, by estimating a luminance mask from low-light image, a luminance mask-guided low-light image generation (LMLIG) module is presented to darken reference normal-light image. In addition, a luminance-independent representation-based low-light image enhancement (LRLIE) module is developed to enhance low-light image by learning luminance-independent representation and incorporating the luminance cue of reference normal-light image. With the LMLIG and LRLIE modules, a bidirectional mapping-based cycle supervision (BMCS) is constructed to facilitate the decoupling of the luminance mask and luminance-independent representation, which further promotes unsupervised low-light enhancement learning with unpaired data. Comprehensive experiments on various challenging benchmark datasets demonstrate that the proposed DeULLE exhibits superior performance.","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":"8 4","pages":"3029-3039"},"PeriodicalIF":5.3000,"publicationDate":"2024-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Emerging Topics in Computational Intelligence","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10466480/","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}

引用次数: 0

Abstract

Enhancing low-light images in an unsupervised manner has become a popular topic due to the challenge of obtaining paired real-world low/normal-light images. Driven by massive available normal-light images, learning a low-light image enhancement network from unpaired data is more practical and valuable. This paper presents an unsupervised low-light image enhancement method (DeULLE) via luminance mask and luminance-independent representation decoupling based on unpaired data. Specifically, by estimating a luminance mask from low-light image, a luminance mask-guided low-light image generation (LMLIG) module is presented to darken reference normal-light image. In addition, a luminance-independent representation-based low-light image enhancement (LRLIE) module is developed to enhance low-light image by learning luminance-independent representation and incorporating the luminance cue of reference normal-light image. With the LMLIG and LRLIE modules, a bidirectional mapping-based cycle supervision (BMCS) is constructed to facilitate the decoupling of the luminance mask and luminance-independent representation, which further promotes unsupervised low-light enhancement learning with unpaired data. Comprehensive experiments on various challenging benchmark datasets demonstrate that the proposed DeULLE exhibits superior performance.

查看原文本刊更多论文

通过亮度掩码和亮度无关表示解耦实现无监督低照度图像增强

由于难以获得真实世界中成对的弱光/正常光图像，以无监督方式增强弱光图像已成为一个热门话题。在大量可用正常光图像的驱动下，从非配对数据中学习低照度图像增强网络更加实用和有价值。本文提出了一种基于非配对数据的无监督弱光图像增强方法（DeULLE），该方法通过亮度掩码和亮度无关表示解耦实现。具体来说，通过从低照度图像中估算亮度掩码，提出了一个亮度掩码引导的低照度图像生成（LMLIG）模块，用于使参考的正常照度图像变暗。此外，还开发了基于亮度无关表示的弱光图像增强（LRLIE）模块，通过学习亮度无关表示并结合参考正常光图像的亮度线索来增强弱光图像。通过 LMLIG 和 LRLIE 模块，构建了基于双向映射的循环监督（BMCS），以促进亮度掩码和亮度无关表示的解耦，从而进一步促进了无配对数据的无监督弱光增强学习。在各种具有挑战性的基准数据集上进行的综合实验证明，所提出的 DeULLE 表现出了卓越的性能。

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分钟内获得全文求助全文

来源期刊

IEEE Transactions on Emerging Topics in Computational Intelligence Mathematics-Control and Optimization

CiteScore

10.30

自引率

7.50%

发文量

147

期刊介绍： The IEEE Transactions on Emerging Topics in Computational Intelligence (TETCI) publishes original articles on emerging aspects of computational intelligence, including theory, applications, and surveys. TETCI is an electronics only publication. TETCI publishes six issues per year. Authors are encouraged to submit manuscripts in any emerging topic in computational intelligence, especially nature-inspired computing topics not covered by other IEEE Computational Intelligence Society journals. A few such illustrative examples are glial cell networks, computational neuroscience, Brain Computer Interface, ambient intelligence, non-fuzzy computing with words, artificial life, cultural learning, artificial endocrine networks, social reasoning, artificial hormone networks, computational intelligence for the IoT and Smart-X technologies.