{"title":"利用相互学习实现伪监督低照度图像增强","authors":"Yu Luo;Bijia You;Guanghui Yue;Jie Ling","doi":"10.1109/TCSVT.2023.3284856","DOIUrl":null,"url":null,"abstract":"Low-light image enhancement (LIE) is important for many high-level vision tasks as the poor visibility of underexposed images can severely degrade the performance of the subsequent image recognition, analysis, etc. Although recent deep-learning-based LIE methods exhibit promising performance, most of them require a large number of paired training images, thereby limiting the practicability to real scenarios. In this paper, we propose a pseudo-supervised LIE method with the integration of mutual learning. Specifically, for the given low-light image, we first use a quadratic curve to generate a pseudo-clear image, which is served as the auxiliary ground truth for supervision, then the pseudo-paired images are simultaneously input to two parallel homogeneous branches to learn the expected enhanced result through the knowledge distillation of two branches via mutual learning. As both the generated image and the input low-light image underlies the desired solution, the mutual learning strategy enables the two branches learn from each other and produce the final results. Extensive experiments demonstrate that the proposed method outperforms most existing unsupervised LIE methods in terms of both qualitative and quantitative evaluations, and also achieves competitive performance against many supervised and semi-supervised methods.","PeriodicalId":13082,"journal":{"name":"IEEE Transactions on Circuits and Systems for Video Technology","volume":null,"pages":null},"PeriodicalIF":8.3000,"publicationDate":"2023-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Pseudo-Supervised Low-Light Image Enhancement With Mutual Learning\",\"authors\":\"Yu Luo;Bijia You;Guanghui Yue;Jie Ling\",\"doi\":\"10.1109/TCSVT.2023.3284856\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Low-light image enhancement (LIE) is important for many high-level vision tasks as the poor visibility of underexposed images can severely degrade the performance of the subsequent image recognition, analysis, etc. Although recent deep-learning-based LIE methods exhibit promising performance, most of them require a large number of paired training images, thereby limiting the practicability to real scenarios. In this paper, we propose a pseudo-supervised LIE method with the integration of mutual learning. Specifically, for the given low-light image, we first use a quadratic curve to generate a pseudo-clear image, which is served as the auxiliary ground truth for supervision, then the pseudo-paired images are simultaneously input to two parallel homogeneous branches to learn the expected enhanced result through the knowledge distillation of two branches via mutual learning. As both the generated image and the input low-light image underlies the desired solution, the mutual learning strategy enables the two branches learn from each other and produce the final results. Extensive experiments demonstrate that the proposed method outperforms most existing unsupervised LIE methods in terms of both qualitative and quantitative evaluations, and also achieves competitive performance against many supervised and semi-supervised methods.\",\"PeriodicalId\":13082,\"journal\":{\"name\":\"IEEE Transactions on Circuits and Systems for Video Technology\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":8.3000,\"publicationDate\":\"2023-06-09\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Transactions on Circuits and Systems for Video Technology\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10147801/\",\"RegionNum\":1,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENGINEERING, ELECTRICAL & ELECTRONIC\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Circuits and Systems for Video Technology","FirstCategoryId":"5","ListUrlMain":"https://ieeexplore.ieee.org/document/10147801/","RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
Pseudo-Supervised Low-Light Image Enhancement With Mutual Learning
Low-light image enhancement (LIE) is important for many high-level vision tasks as the poor visibility of underexposed images can severely degrade the performance of the subsequent image recognition, analysis, etc. Although recent deep-learning-based LIE methods exhibit promising performance, most of them require a large number of paired training images, thereby limiting the practicability to real scenarios. In this paper, we propose a pseudo-supervised LIE method with the integration of mutual learning. Specifically, for the given low-light image, we first use a quadratic curve to generate a pseudo-clear image, which is served as the auxiliary ground truth for supervision, then the pseudo-paired images are simultaneously input to two parallel homogeneous branches to learn the expected enhanced result through the knowledge distillation of two branches via mutual learning. As both the generated image and the input low-light image underlies the desired solution, the mutual learning strategy enables the two branches learn from each other and produce the final results. Extensive experiments demonstrate that the proposed method outperforms most existing unsupervised LIE methods in terms of both qualitative and quantitative evaluations, and also achieves competitive performance against many supervised and semi-supervised methods.
期刊介绍:
The IEEE Transactions on Circuits and Systems for Video Technology (TCSVT) is dedicated to covering all aspects of video technologies from a circuits and systems perspective. We encourage submissions of general, theoretical, and application-oriented papers related to image and video acquisition, representation, presentation, and display. Additionally, we welcome contributions in areas such as processing, filtering, and transforms; analysis and synthesis; learning and understanding; compression, transmission, communication, and networking; as well as storage, retrieval, indexing, and search. Furthermore, papers focusing on hardware and software design and implementation are highly valued. Join us in advancing the field of video technology through innovative research and insights.