EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Infrared-Visible Image Fusion Meets Object Detection: Towards Unified Optimization for Multimodal Perception

Xiantai Xiang, Guangyao Zhou, Ben Niu, Zongxu Pan, Lijia Huang, Wenshuai Li, Zixiao Wen, Jiamin Qi, Wanxin Gao

Remote Sensing · 04.11.2025 · 17 (21) · 3637

DOI: 10.3390/rs17213637 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 04.11.2025. Verfasst von Xiantai Xiang und 8 weiteren Autor:innen. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 82 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Infrared-visible image fusion and object detection are crucial components in remote sensing applications, each offering unique advantages. Recent research has increasingly sought to combine these tasks to enhance object detection performance. However, the integration of these tasks presents several challenges, primarily due to two overlooked issues: (i) existing infrared-visible image fusion methods often fail to adequately focus on fine-grained or dense information, and (ii) while joint optimization methods can improve fusion quality and downstream task performance, their multi-stage training processes often reduce efficiency and limit the network’s global optimization capability. To address these challenges, we propose the UniFusOD method, an efficient end-to-end framework that simultaneously optimizes both infrared-visible image fusion and object detection tasks. The method integrates Fine-Grained Region Attention (FRA) for region-specific attention operations at different granularities, enhancing the model’s ability to capture complex information. Furthermore, UnityGrad is introduced to balance the gradient conflicts between fusion and detection tasks, stabilizing the optimization process. Extensive experiments demonstrate the superiority and robustness of our approach. Not only does UniFusOD achieve excellent results in image fusion, but it also provides significant improvements in object detection performance. The method exhibits remarkable robustness across various tasks, achieving a 0.8 and 1.9 mAP50 improvement over state-of-the-art methods on the DroneVehicle dataset for rotated object detection and the M3FD dataset for horizontal object detection, respectively.

Zitieren

APA

Xiang, X., Zhou, G., Niu, B., Pan, Z., Huang, L., Li, W., Wen, Z., Qi, J., & Gao, W. (2025). Infrared-Visible Image Fusion Meets Object Detection: Towards Unified Optimization for Multimodal Perception. Remote Sensing, 17(21), 3637. https://doi.org/10.3390/rs17213637

Vancouver

Xiang X, Zhou G, Niu B, Pan Z, Huang L, Li W, et al. Infrared-Visible Image Fusion Meets Object Detection: Towards Unified Optimization for Multimodal Perception. Remote Sensing. 2025;17(21):3637. doi:10.3390/rs17213637

BibTeX
@article{Xiang2025,
  author = {Xiang, Xiantai and Zhou, Guangyao and Niu, Ben and Pan, Zongxu and Huang, Lijia and Li, Wenshuai and Wen, Zixiao and Qi, Jiamin and Gao, Wanxin},
  title = {Infrared-Visible Image Fusion Meets Object Detection: Towards Unified Optimization for Multimodal Perception},
  journal = {Remote Sensing},
  year = {2025},
  volume = {17},
  number = {21},
  pages = {3637},
  doi = {10.3390/rs17213637}
}
Kostenlos starten →