CDTFusion: Crossing Domain and Task for Infrared and Visible Image Fusion

Wenda Zhao, Ruikang K. Wang, Haipeng Wang, You He, Huchuan LuIEEE TPAMI 2025 · DOI

Abstract

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.
BibTeX
@article{zhao2025cdtfusion,
  author = {Wenda Zhao and Ruikang K. Wang and Haipeng Wang and You He and Huchuan Lu},
  title = {{CDTFusion: Crossing Domain and Task for Infrared and Visible Image Fusion}},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2025},
  doi = {10.1109/tpami.2025.3614704},
}

Loading related content...

Figure