DHAFGan: A dense hybrid attention fusion generative adversarial network for infrared and visible image fusion
4 affiliations
- 1Business School, Jiangsu Vocational College of Electronics and Information, Huaian, China
- 2School of Transportation Engineering, Huai’an University, Huaian, China
- 3Smart Campus Service Center, Jiangsu Vocational College of Finance and Economics, Huai’an, China
- 4School of Artificial Intelligence, Nanjing University of Information Science and Technology, Nanjing, China
Abstract
Aiming at the problems existing in the current infrared and visible light image fusion algorithms, such as insufficient perception of typical features, poor visual representation of the fusion results, and insufficient utilization of important secondary information, this paper proposes an infrared and visible light image fusion algorithm based on shallow-deep feature extraction and dual-channel hybrid attention. Firstly, a shallow-deep feature extraction module is constructed. This module utilizes shallow convolutional layers and deep multi-scale receptive field units to extract surface-level features and deep semantic information from the source images, respectively, thereby achieving multi-level multimodal feature extraction. Secondly, Dual-Channel Hybrid Attention Fusion Module (DCAFM) is constructed. Spatial attention is focused on the salient areas of the image, and channel attention is used to strengthen the feature channels, thereby enhancing the fusion ability of multimodal features. Finally, primary and secondary feature loss functions are formulated to constrain both the generator and discriminator, facilitating the extraction of latent secondary feature information from the source images. Experimental results on the DroneVehicle dataset demonstrate that the proposed algorithm achieves superior performance in both subjective visual evaluation and objective metrics. Quantitative evaluations show that our method outperforms seven state-of-the-art approaches, achieving the highest scores in standard deviation (SD = 9.3541), mutual information (MI = 2.4321), and peak signal-to-noise ratio (PSNR = 65.7852), while ranking second in average gradient (AG = 3.9854). The fused images generated by our method not only align with human visual perception characteristics but also retain rich detailed information, effectively preserving both dominant and subtle features from the source modalities.
Related
- Conditional Generative Adversarial Network for the simulation of seabird trajectories based on environmental data
- Generative Adversarial Networks for Omics Data: An Overview and Future Directions for Livestock Applications
- Hi-cGAN: Prediction of Hi-C interaction matrices with conditional generative adversarial networks
- MSCF-DM: center-site-aware attention and gated multi-scale fusion network for cross-species DNA methylation site prediction
- VAD-EmotionNet: a spatial-spectral attention network for EEG emotion recognition in the 3D affective space
BibTeX
@article{hong2026dhafgan,
title = {{DHAFGan: A dense hybrid attention fusion generative adversarial network for infrared and visible image fusion}},
author = {Qiong Hong and Zhonghua Xu and Dongli Qin and Yuhui Zheng and Hao Zhang},
journal = {PLOS One},
year = {2026},
month = sep,
doi = {10.1371/journal.pone.0346471},
url = {https://doi.org/10.1371/journal.pone.0346471},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - DHAFGan: A dense hybrid attention fusion generative adversarial network for infrared and visible image fusion
AU - Qiong Hong
AU - Zhonghua Xu
AU - Dongli Qin
AU - Yuhui Zheng
AU - Hao Zhang
PY - 2026
DA - 2026/09/11
JO - PLOS One
DO - 10.1371/journal.pone.0346471
UR - https://doi.org/10.1371/journal.pone.0346471
AB - Aiming at the problems existing in the current infrared and visible light image fusion algorithms, such as insufficient perception of typical features, poor visual representation of the fusion results, and insufficient utilization of important secondary information, this paper proposes an infrared and visible light image fusion algorithm based on shallow-deep feature extraction and dual-channel hybrid attention. Firstly, a shallow-deep feature extraction module is constructed. This module utilizes shallow convolutional layers and deep multi-scale receptive field units to extract surface-level features and deep semantic information from the source images, respectively, thereby achieving multi-level multimodal feature extraction. Secondly, Dual-Channel Hybrid Attention Fusion Module (DCAFM) is constructed. Spatial attention is focused on the salient areas of the image, and channel attention is used to strengthen the feature channels, thereby enhancing the fusion ability of multimodal features. Finally, primary and secondary feature loss functions are formulated to constrain both the generator and discriminator, facilitating the extraction of latent secondary feature information from the source images. Experimental results on the DroneVehicle dataset demonstrate that the proposed algorithm achieves superior performance in both subjective visual evaluation and objective metrics. Quantitative evaluations show that our method outperforms seven state-of-the-art approaches, achieving the highest scores in standard deviation (SD = 9.3541), mutual information (MI = 2.4321), and peak signal-to-noise ratio (PSNR = 65.7852), while ranking second in average gradient (AG = 3.9854). The fused images generated by our method not only align with human visual perception characteristics but also retain rich detailed information, effectively preserving both dominant and subtle features from the source modalities.
SN - 1932-6203
ER -