Model-based Bayesian Fusion-Net for infrared and visible image fusion

Abstract Infrared and visible image fusion aims to generate fused images that maintain the advantages of each source such as temperature information and detailed textures. This paper presents Bayesian Model-based Fusion-Net, a novel approach for infrared and visible image fusion. By formulating imag...

Full description

Saved in:
Bibliographic Details
Main Authors: Wang Li, Kuang Yafang, Cai Ziyi, Chu Ning, Mohammad-Djafari Ali
Format: Article
Language:English
Published: SpringerOpen 2025-08-01
Series:EURASIP Journal on Image and Video Processing
Subjects:
Online Access:https://doi.org/10.1186/s13640-025-00680-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849235071724158976
author Wang Li
Kuang Yafang
Cai Ziyi
Chu Ning
Mohammad-Djafari Ali
author_facet Wang Li
Kuang Yafang
Cai Ziyi
Chu Ning
Mohammad-Djafari Ali
author_sort Wang Li
collection DOAJ
description Abstract Infrared and visible image fusion aims to generate fused images that maintain the advantages of each source such as temperature information and detailed textures. This paper presents Bayesian Model-based Fusion-Net, a novel approach for infrared and visible image fusion. By formulating image fusion as an inverse problem within a hierarchical Bayesian framework, our method leverages physical priors and data-driven techniques to enhance model interpretability and transferability. Compared to traditional and deep learning-based fusion methods, the proposed Bayesian Model-based Fusion-Net achieves promising performance with significantly reduced computational complexity (0.07G FLOPs). Extensive experiments on multiple datasets, including industrial public dataset, demonstrate the effectiveness of the proposed method in preserving texture details, maintaining structural integrity, and enhancing feature clarity. Furthermore, our approach exhibits robustness when trained with limited data, maintaining consistent performance even when using only 10% of the training dataset. These characteristics make the proposed Bayesian Fusion-Net particularly suitable for industrial monitoring applications where computational resources and the amount of training dataset are limited.
format Article
id doaj-art-4b75228005ea4bdab02a884b9cbfa50e
institution Kabale University
issn 1687-5281
language English
publishDate 2025-08-01
publisher SpringerOpen
record_format Article
series EURASIP Journal on Image and Video Processing
spelling doaj-art-4b75228005ea4bdab02a884b9cbfa50e2025-08-20T04:02:55ZengSpringerOpenEURASIP Journal on Image and Video Processing1687-52812025-08-012025112510.1186/s13640-025-00680-5Model-based Bayesian Fusion-Net for infrared and visible image fusionWang Li0Kuang Yafang1Cai Ziyi2Chu Ning3Mohammad-Djafari Ali4School of Mathematics and Statistics, Central South UniversitySchool of Mathematics and Statistics, Central South UniversitySchool of Mathematics and Statistics, Central South UniversityNingbo Institute of Digital Twin (IDT), Ningbo Eastern Institute of TechnologyNingbo Institute of Digital Twin (IDT), Ningbo Eastern Institute of TechnologyAbstract Infrared and visible image fusion aims to generate fused images that maintain the advantages of each source such as temperature information and detailed textures. This paper presents Bayesian Model-based Fusion-Net, a novel approach for infrared and visible image fusion. By formulating image fusion as an inverse problem within a hierarchical Bayesian framework, our method leverages physical priors and data-driven techniques to enhance model interpretability and transferability. Compared to traditional and deep learning-based fusion methods, the proposed Bayesian Model-based Fusion-Net achieves promising performance with significantly reduced computational complexity (0.07G FLOPs). Extensive experiments on multiple datasets, including industrial public dataset, demonstrate the effectiveness of the proposed method in preserving texture details, maintaining structural integrity, and enhancing feature clarity. Furthermore, our approach exhibits robustness when trained with limited data, maintaining consistent performance even when using only 10% of the training dataset. These characteristics make the proposed Bayesian Fusion-Net particularly suitable for industrial monitoring applications where computational resources and the amount of training dataset are limited.https://doi.org/10.1186/s13640-025-00680-5Infrared and visible image fusionBayesian inferenceDeep unfoldingIndustrial abnormal detection
spellingShingle Wang Li
Kuang Yafang
Cai Ziyi
Chu Ning
Mohammad-Djafari Ali
Model-based Bayesian Fusion-Net for infrared and visible image fusion
EURASIP Journal on Image and Video Processing
Infrared and visible image fusion
Bayesian inference
Deep unfolding
Industrial abnormal detection
title Model-based Bayesian Fusion-Net for infrared and visible image fusion
title_full Model-based Bayesian Fusion-Net for infrared and visible image fusion
title_fullStr Model-based Bayesian Fusion-Net for infrared and visible image fusion
title_full_unstemmed Model-based Bayesian Fusion-Net for infrared and visible image fusion
title_short Model-based Bayesian Fusion-Net for infrared and visible image fusion
title_sort model based bayesian fusion net for infrared and visible image fusion
topic Infrared and visible image fusion
Bayesian inference
Deep unfolding
Industrial abnormal detection
url https://doi.org/10.1186/s13640-025-00680-5
work_keys_str_mv AT wangli modelbasedbayesianfusionnetforinfraredandvisibleimagefusion
AT kuangyafang modelbasedbayesianfusionnetforinfraredandvisibleimagefusion
AT caiziyi modelbasedbayesianfusionnetforinfraredandvisibleimagefusion
AT chuning modelbasedbayesianfusionnetforinfraredandvisibleimagefusion
AT mohammaddjafariali modelbasedbayesianfusionnetforinfraredandvisibleimagefusion