EUVIMEDEUVIMED entdecken
Crossref

Task-Generalized Adaptive Cross-Domain Learning for Multimodal Image Fusion

Mengyu Wang, Zhenyu Liu, Kun Li, Yu Wang, Yuwei Wang, Yanyan Wei, Fei Wang

IEEE Transactions on Multimedia · 2026 · 28 · 4624-4637

DOI: 10.1109/tmm.2026.3660142 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Multimedia, 2026. Verfasst von Mengyu Wang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Jiangxi Province of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multimodal Image Fusion (MMIF) aims to integrate complementary information from different imaging modalities to overcome the limitations of individual sensors. It enhances image quality and facilitates downstream applications such as remote sensing, medical diagnostics, and robotics. Despite significant advancements, current MMIF methods still face challenges such as modality misalignment, high-frequency detail destruction, and task-specific limitations. To address these challenges, we propose AdaSFFuse, a novel framework for task-generalized MMIF through adaptive cross-domain co-fusion learning. AdaSFFuse introduces two key innovations: the Adaptive Approximate Wavelet Transform (AdaWAT) for frequency decoupling, and the Spatial-Frequency Mamba Blocks for efficient multimodal fusion. AdaWAT adaptively separates the high- and low-frequency components of multimodal images from different scenes, enabling fine-grained extraction and alignment of distinct frequency characteristics for each modality. The Spatial-Frequency Mamba Blocks facilitate cross-domain fusion in both spatial and frequency domains, enhancing this process. These blocks dynamically adjust through learnable mappings to ensure robust fusion across diverse modalities. By combining these components, AdaSFFuse improves the alignment and integration of multimodal features, reduces frequency loss, and preserves critical details. Extensive experiments on four MMIF tasks—Infrared-Visible Image Fusion (IVF), Multi-Focus Image Fusion (MFF), Multi-Exposure Image Fusion (MEF), and Medical Image Fusion (MIF)—demonstrate AdaSFFuse's superior fusion performance, ensuring both low computational cost and a compact network, offering a strong balance between performance and efficiency.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Jiangxi Province of China

Zitieren

APA

Wang, M., Liu, Z., Li, K., Wang, Y., Wang, Y., Wei, Y., & Wang, F. (2026). Task-Generalized Adaptive Cross-Domain Learning for Multimodal Image Fusion. IEEE Transactions on Multimedia, 28, 4624-4637. https://doi.org/10.1109/tmm.2026.3660142

Vancouver

Wang M, Liu Z, Li K, Wang Y, Wang Y, Wei Y, et al. Task-Generalized Adaptive Cross-Domain Learning for Multimodal Image Fusion. IEEE Transactions on Multimedia. 2026;28:4624-4637. doi:10.1109/tmm.2026.3660142

BibTeX
@article{Wang2026,
  author = {Wang, Mengyu and Liu, Zhenyu and Li, Kun and Wang, Yu and Wang, Yuwei and Wei, Yanyan and Wang, Fei},
  title = {Task-Generalized Adaptive Cross-Domain Learning for Multimodal Image Fusion},
  journal = {IEEE Transactions on Multimedia},
  year = {2026},
  volume = {28},
  pages = {4624--4637},
  doi = {10.1109/tmm.2026.3660142}
}
Kostenlos starten →