View in EDS

SDSFusion: A Semantic-Aware Infrared and Visible Image Fusion Network for Degraded Scenes.

Saved in:
Bibliographic Details
Title: SDSFusion: A Semantic-Aware Infrared and Visible Image Fusion Network for Degraded Scenes.
Authors: Chen, Jun1 chenjun71983@163.com, Yang, Liling1, Yu, Wei1, Gong, Wenping2, Cai, Zhanchuan3 zccai@must.edu.mo, Ma, Jiayi4 jyma2010@gmail.com
Source: IEEE Transactions on Image Processing. 2025, Vol. 34, p3139-3153. 15p.
Subjects: Image fusion, Image processing, Digital images, Image enhancement (Imaging systems), Imaging systems
Abstract: A single-modal infrared or visible image offers limited representation in scenes with lighting degradation or extreme weather. We propose a multi-modal fusion framework, named SDSFusion, for all-day and all-weather infrared and visible image fusion. SDSFusion exploits the commonality in image processing to achieve enhancement, fusion, and semantic task interaction in a unified framework guided by semantic awareness and multi-scale features and losses. To address the disparity between infrared and visible images in degraded scenes, we differentiate modal features in a unified fusion model. Unlike existing joint fusion methods, we propose an adversarial generative network that refines the reconstruction of low-light images by embedding fused features. It provides feature-level brightness supplementation and image reconstruction to refine brightness and contrast. Extensive experiments in degraded scenes confirm that our approach is superior to state-of-the-art approaches in visual quality and performance, demonstrating the effectiveness of interaction improvement. The code will be posted at: https://github.com/Liling-yang/SDSFusion. [ABSTRACT FROM AUTHOR]
Copyright of IEEE Transactions on Image Processing is the property of IEEE 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
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 191897057
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: SDSFusion: A Semantic-Aware Infrared and Visible Image Fusion Network for Degraded Scenes.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Chen%2C+Jun%22">Chen, Jun</searchLink><relatesTo>1</relatesTo><i> chenjun71983@163.com</i><br /><searchLink fieldCode="AR" term="%22Yang%2C+Liling%22">Yang, Liling</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Yu%2C+Wei%22">Yu, Wei</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Gong%2C+Wenping%22">Gong, Wenping</searchLink><relatesTo>2</relatesTo><br /><searchLink fieldCode="AR" term="%22Cai%2C+Zhanchuan%22">Cai, Zhanchuan</searchLink><relatesTo>3</relatesTo><i> zccai@must.edu.mo</i><br /><searchLink fieldCode="AR" term="%22Ma%2C+Jiayi%22">Ma, Jiayi</searchLink><relatesTo>4</relatesTo><i> jyma2010@gmail.com</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22IEEE+Transactions+on+Image+Processing%22">IEEE Transactions on Image Processing</searchLink>. 2025, Vol. 34, p3139-3153. 15p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Image+fusion%22">Image fusion</searchLink><br /><searchLink fieldCode="DE" term="%22Image+processing%22">Image processing</searchLink><br /><searchLink fieldCode="DE" term="%22Digital+images%22">Digital images</searchLink><br /><searchLink fieldCode="DE" term="%22Image+enhancement+%28Imaging+systems%29%22">Image enhancement (Imaging systems)</searchLink><br /><searchLink fieldCode="DE" term="%22Imaging+systems%22">Imaging systems</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: A single-modal infrared or visible image offers limited representation in scenes with lighting degradation or extreme weather. We propose a multi-modal fusion framework, named SDSFusion, for all-day and all-weather infrared and visible image fusion. SDSFusion exploits the commonality in image processing to achieve enhancement, fusion, and semantic task interaction in a unified framework guided by semantic awareness and multi-scale features and losses. To address the disparity between infrared and visible images in degraded scenes, we differentiate modal features in a unified fusion model. Unlike existing joint fusion methods, we propose an adversarial generative network that refines the reconstruction of low-light images by embedding fused features. It provides feature-level brightness supplementation and image reconstruction to refine brightness and contrast. Extensive experiments in degraded scenes confirm that our approach is superior to state-of-the-art approaches in visual quality and performance, demonstrating the effectiveness of interaction improvement. The code will be posted at: https://github.com/Liling-yang/SDSFusion. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of IEEE Transactions on Image Processing is the property of IEEE 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=191897057
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1109/TIP.2025.3571339
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 15
        StartPage: 3139
    Subjects:
      – SubjectFull: Image fusion
        Type: general
      – SubjectFull: Image processing
        Type: general
      – SubjectFull: Digital images
        Type: general
      – SubjectFull: Image enhancement (Imaging systems)
        Type: general
      – SubjectFull: Imaging systems
        Type: general
    Titles:
      – TitleFull: SDSFusion: A Semantic-Aware Infrared and Visible Image Fusion Network for Degraded Scenes.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Chen, Jun
      – PersonEntity:
          Name:
            NameFull: Yang, Liling
      – PersonEntity:
          Name:
            NameFull: Yu, Wei
      – PersonEntity:
          Name:
            NameFull: Gong, Wenping
      – PersonEntity:
          Name:
            NameFull: Cai, Zhanchuan
      – PersonEntity:
          Name:
            NameFull: Ma, Jiayi
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Text: 2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 10577149
          Numbering:
            – Type: volume
              Value: 34
          Titles:
            – TitleFull: IEEE Transactions on Image Processing
              Type: main
ResultId 1