App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 6

MS-DAFNet: multi-scale dual-attention fusion network for infrared and visible image fusion

Zeng Guangqun
Huang Zhiyong
Wang Ruijin
Zhang Fengli
School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 514000, China
DOI: 10.19734/j.issn.1001-3695.2025.09.0405

Abstract

The goal of infrared and visible image fusion is to generate a single image rich in information and natural in appearance to enhance scene perception. To address issues such as insufficient preservation of thermal targets and details, along with artifact generation caused by modal feature differences in fusing these two types of images, this paper proposes a multi-scale dual attention network named MS-DAFNet. The core of MS-DAFNet is a dual attention fusion module that operates in parallel at two key feature levels: a global context attention module captures long-range spatial dependencies, while a patch-based adaptive cross-attention module performs fine-grained cross-modal feature interaction. The method introduces a contrastive learning pre-training strategy to effectively bridge the modality gap, enabling the network to learn more discriminative multi-scale feature representations. Additionally, a hierarchical gated decoder is designed to adaptively integrate multi-scale feature streams for high-quality fused image reconstruction. On the TNO grayscale dataset, MS-DAFNet achieves an entropy of 7.121, a peak signal-to-noise ratio of 14.8413, and a structural similarity of 1.076; the method also demonstrates outstanding performance on the M3FD color dataset. Experimental results fully confirm that MS-DAFNet generates fused images with richer information, more salient targets, and clearer details.

Foundation Support

国家自然科学基金资助项目(U2333207,62271128)
成都重点研发支持计划项目(2025-YF08-00128-GX,2025-YF12-00029-RC)
四川省科技计划重点研发项目(2022ZDZX0004,2025YFHZ0302)
四川省科技计划"揭榜挂帅"项目(2023YFG0374)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2025.09.0405
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 6

Publish History

[2026-02-04] Accepted Paper

Cite This Article

曾广群, 黄智勇, 王瑞锦, 等. 基于多尺度双注意力网络的红外与可见光图像融合 [J]. 计算机应用研究, 2026, 43 (6). (2026-02-25). https://doi.org/10.19734/j.issn.1001-3695.2025.09.0405. (Zeng Guangqun, Huang Zhiyong, Wang Ruijin, et al. MS-DAFNet: multi-scale dual-attention fusion network for infrared and visible image fusion [J]. Application Research of Computers, 2026, 43 (6). (2026-02-25). https://doi.org/10.19734/j.issn.1001-3695.2025.09.0405. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)