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