CDTFusion: Crossing Domain and Task for Infrared and Visible Image Fusion
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-02 · 48 (2) · 1456-1469
DOI: 10.1109/tpami.2025.3614704 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-02. Verfasst von Wenda Zhao und 4 weiteren Autor:innen. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 52 Literaturangaben. Gefördert von: National Natural Science Foundation of China Youth Program.
Abstract (Originalsprache)
Infrared and visible images present different domains that hinder the fusion process, thereby losing texture details. Besides, the low-level fusion and subsequent high-level segmentation appear cross-task feature gap that impedes their mutual promotion, causing blurred object edges. Addressing the above issues, this paper proposes a novel infrared and visible image fusion method that simultaneously crosses domain and task. First, a swap image translation strategy is built to transfer the features of visible and infrared images into an adaptive domain. Meanwhile, a global-local constraint is introduced to achieve overall domain space transfer, and shorten their feature distance. Second, a task interaction & query module is designed to explore the cross-task feature interactive relationship, which is then used as a bridge to realize the gradient backpropagation. Thus, a fine-grained mapping from the segmentation feature to fusion feature is obtained. Extensive experiments demonstrate that the proposed method exhibits superior fusion and segmentation performance than the state-of-the-art methods.
Förderung
- National Natural Science Foundation of China Youth Program
Zitieren
APA
Zhao, W., Wang, W., Wang, H., He, Y., & Lu, H. (2026). CDTFusion: Crossing Domain and Task for Infrared and Visible Image Fusion. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(2), 1456-1469. https://doi.org/10.1109/tpami.2025.3614704
Vancouver
Zhao W, Wang W, Wang H, He Y, Lu H. CDTFusion: Crossing Domain and Task for Infrared and Visible Image Fusion. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(2):1456-1469. doi:10.1109/tpami.2025.3614704
BibTeX
@article{Zhao2026,
author = {Zhao, Wenda and Wang, Wenbo and Wang, Haipeng and He, You and Lu, Huchuan},
title = {CDTFusion: Crossing Domain and Task for Infrared and Visible Image Fusion},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2026},
volume = {48},
number = {2},
pages = {1456--1469},
doi = {10.1109/tpami.2025.3614704}
}
EUVIMED