View in EDS HTML Full Text PDF Full Text

Unsupervised low-light image enhancement by data augmentation and contrastive learning.

Saved in:
Bibliographic Details
Title: Unsupervised low-light image enhancement by data augmentation and contrastive learning.
Authors: Junzhe, Shao1 (AUTHOR), Zhibin, Zhang2 (AUTHOR) zhangzhibin@ict.ac.cn
Source: Imaging Science Journal. May2025, Vol. 73 Issue 3, p354-362. 9p.
Subjects: Image databases, Data augmentation, Visual perception, Image intensifiers, Data modeling
Abstract: Today, with the increasing demand for visual perception and high-level computational vision tasks, the field of low-light enhancement is rapidly developing. However, models trained on existing datasets often fail or suffer significant performance degradation in real-world low-light scenarios. This performance degradation is frequently due to the limitations of current databases, which typically contain small quantities of paired images of a single type. This article proposes an unsupervised model with a unique data augmentation technique that transforms a regular image database into a paired image database. By adjusting image parameters during training to change exposure, a regular image database can be converted into a paired one. The model restores low-exposure images by extracting lighting features through comparative learning. Evaluations of the LOL and DIV2K datasets demonstrate the proposed model's effectiveness, achieving notable results in low-light image enhancement. This method removes dataset restrictions, broadening the model's range of applications. [ABSTRACT FROM AUTHOR]
Copyright of Imaging Science Journal is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 184650612
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Unsupervised low-light image enhancement by data augmentation and contrastive learning.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Junzhe%2C+Shao%22">Junzhe, Shao</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhibin%2C+Zhang%22">Zhibin, Zhang</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> zhangzhibin@ict.ac.cn</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Imaging+Science+Journal%22">Imaging Science Journal</searchLink>. May2025, Vol. 73 Issue 3, p354-362. 9p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Image+databases%22">Image databases</searchLink><br /><searchLink fieldCode="DE" term="%22Data+augmentation%22">Data augmentation</searchLink><br /><searchLink fieldCode="DE" term="%22Visual+perception%22">Visual perception</searchLink><br /><searchLink fieldCode="DE" term="%22Image+intensifiers%22">Image intensifiers</searchLink><br /><searchLink fieldCode="DE" term="%22Data+modeling%22">Data modeling</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Today, with the increasing demand for visual perception and high-level computational vision tasks, the field of low-light enhancement is rapidly developing. However, models trained on existing datasets often fail or suffer significant performance degradation in real-world low-light scenarios. This performance degradation is frequently due to the limitations of current databases, which typically contain small quantities of paired images of a single type. This article proposes an unsupervised model with a unique data augmentation technique that transforms a regular image database into a paired image database. By adjusting image parameters during training to change exposure, a regular image database can be converted into a paired one. The model restores low-exposure images by extracting lighting features through comparative learning. Evaluations of the LOL and DIV2K datasets demonstrate the proposed model's effectiveness, achieving notable results in low-light image enhancement. This method removes dataset restrictions, broadening the model's range of applications. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Imaging Science Journal is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=184650612
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1080/13682199.2024.2395751
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 9
        StartPage: 354
    Subjects:
      – SubjectFull: Image databases
        Type: general
      – SubjectFull: Data augmentation
        Type: general
      – SubjectFull: Visual perception
        Type: general
      – SubjectFull: Image intensifiers
        Type: general
      – SubjectFull: Data modeling
        Type: general
    Titles:
      – TitleFull: Unsupervised low-light image enhancement by data augmentation and contrastive learning.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Junzhe, Shao
      – PersonEntity:
          Name:
            NameFull: Zhibin, Zhang
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 05
              Text: May2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 13682199
          Numbering:
            – Type: volume
              Value: 73
            – Type: issue
              Value: 3
          Titles:
            – TitleFull: Imaging Science Journal
              Type: main
ResultId 1