EUVIMEDEUVIMED entdecken
Crossref

BusReF: Infrared-Visible Images Registration and Fusion Focus on Reconstructible Area Using One Set of Features

Zeyang Zhang, Hui Li, Tianyang Xu, Xiaojun Wu, Congcong Bian, Josef Kittler

ACM Transactions on Multimedia Computing, Communications, and Applications · 31.01.2026 · 22 (1) · 1-19

DOI: 10.1145/3773769 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 12.01.2026. Verfasst von Zeyang Zhang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 60 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities, Basic Research Program of Jiangsu.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In multi-modal imaging scenarios, the misalignment of images presents a persistent challenge. Conventional image fusion algorithms, aiming to enhance the performance of downstream vision tasks, presuppose strictly registered inputs to achieve satisfactory results. To relax this assumption, a common approach is to register the images first; however, existing multi-modal registration methods are often hindered by complex architectures and a heavy reliance on semantic information. This article proposes BusRef, a unified framework that jointly addresses image registration and fusion, with a specific focus on the Infrared-Visible Image Registration and Fusion (IVRF) task. Within this framework, unaligned image pairs are processed through three sequential stages: coarse registration, fine registration, and fusion. We demonstrate that this integrated approach enables more robust and accurate IVRF. Key to our framework is a novel training and evaluation strategy that employs masks to mitigate the influence of non-reconstructible regions on the loss function, thereby significantly improving the model’s accuracy and robustness. Furthermore, we introduce a gradient-aware fusion network designed to effectively preserve complementary information from both modalities. Comprehensive experiments demonstrate that BusRef achieves superior performance when compared against various state-of-the-art registration and fusion algorithms. Our code is available at https://github.com/Yukarizz/BusReF .

Förderung

  • National Natural Science Foundation of China
  • Fundamental Research Funds for the Central Universities
  • Basic Research Program of Jiangsu
  • 111 Project of Ministry of Education of China

Zitieren

APA

Zhang, Z., Li, H., Xu, T., Wu, X., Bian, C., & Kittler, J. (2026). BusReF: Infrared-Visible Images Registration and Fusion Focus on Reconstructible Area Using One Set of Features. ACM Transactions on Multimedia Computing, Communications, and Applications, 22(1), 1-19. https://doi.org/10.1145/3773769

Vancouver

Zhang Z, Li H, Xu T, Wu X, Bian C, Kittler J. BusReF: Infrared-Visible Images Registration and Fusion Focus on Reconstructible Area Using One Set of Features. ACM Transactions on Multimedia Computing, Communications, and Applications. 2026;22(1):1-19. doi:10.1145/3773769

BibTeX
@article{Zhang2026,
  author = {Zhang, Zeyang and Li, Hui and Xu, Tianyang and Wu, Xiaojun and Bian, Congcong and Kittler, Josef},
  title = {BusReF: Infrared-Visible Images Registration and Fusion Focus on Reconstructible Area Using One Set of Features},
  journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
  year = {2026},
  volume = {22},
  number = {1},
  pages = {1--19},
  doi = {10.1145/3773769}
}
Kostenlos starten →