ORIGINAL RESEARCH article
Front. Phys.
Sec. Radiation Detectors and Imaging
Volume 13 - 2025 | doi: 10.3389/fphy.2025.1599968
This article is part of the Research TopicMulti-Sensor Imaging and Fusion: Methods, Evaluations, and Applications, Volume IIIView all 9 articles
Target-Aware Unregistered Infrared and Visible Image Fusion
Provisionally accepted
- Qujing Power Supply Bureau, Yunnan Power Grid Co., Ltd., Qujing, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Infrared (IR) and visible (VI) image fusion can provide richer texture details for subsequent object detection tasks. Conversely, object detection can offer semantic information about targets, which in turn helps improve the quality of the fused images. As a result, joint learning approaches that integrate infrared-visible image fusion and object detection have attracted increasing attention.However, existing methods typically assume that the input source images are perfectly aligned spatially-an assumption that does not hold in real-world applications. To address this issue, we propose a novel method that enables mutual enhancement between infrared-visible image fusion and object detection, specifically designed to handle misaligned source images. The core idea is to use the object detection loss, propagated via backpropagation, to guide the training of the fusion network, while a specially designed loss function mitigates the modality gap between infrared and visible images. Comprehensive experiments on three public datasets demonstrate the effectiveness of our approach. In addition, our approach can be used with other radiation frequencies where different modalities require image fusion like, for example, radio-frequency, xand gamma rays used in medical imaging.
Keywords: Infrared and visible image fusion, object detection, Feature alignment, Target-aware, Unregistered
Received: 25 Mar 2025; Accepted: 19 May 2025.
Copyright: © 2025 Hu, Wang, Zhang, Liu, Che, Dong and Kong. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Zheng Liu, Qujing Power Supply Bureau, Yunnan Power Grid Co., Ltd., Qujing, China
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.