Cross-Modal Image Fusion via Structure Preservation and Detail Enhancement Optimization
Sensors · 03.08.2026 · 26 (15) · 4880
DOI: 10.3390/s26154880 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 03.08.2026. Verfasst von Xiaoxia Wang und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Information and Communication Engineering, North University of China, Taiyuan 030051, China. Die Arbeit nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fundamental Research Program of Shanxi Province, Fundamental Research Program of Shanxi Province under Grant Intelligent Perception and Information Fusion Laboratory.
Abstract (Originalsprache)
Existing end-to-end infrared–visible fusion methods often blur edges, smooth textures and weaken target-to-background contrast. We therefore propose Structure–Detail Constrained Fusion (SDC-Fusion), a frequency-decoupled framework with separate constraints on structure and detail. The proposed method employs the Haar wavelet transform to decompose the source images into low-frequency structural and high-frequency detail components. The high-frequency branch uses a local directional-energy prior to construct the target guidance. Unlike existing Rectified Flow-based approaches that operate on the full image or a generic latent representation, our gated module applies Rectified Flow only to the high-frequency wavelet subbands. It learns a few-step residual trajectory from the visible high-frequency coefficients to the target representation, enhancing infrared target boundaries and visible textures without altering low-frequency structure. In the low-frequency branch, adaptive weighting, four-directional Mamba scanning, and multi-dilation depthwise convolutions are integrated to preserve global luminance and background structure while optimizing local grayscale transitions. Comparative experiments against eleven representative fusion methods on the MSRS and M3FD datasets show that SDC-Fusion ranks first in SSIM, VIF, Qabf, SF, and PSNR on MSRS, and first in SSIM, VIF, Qabf, SD, and PSNR on M3FD, while ranking second in the remaining two metrics on each dataset. Relative to the strongest competing result, the largest improvements reach 10.44% in SF on MSRS and 5.72% in VIF on M3FD. The model contains 0.535 M parameters and requires 67.5 G FLOPs.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Information and Communication Engineering, North University of China, Taiyuan 030051, China.
ORCID-Profile: Xiaoxia Wang, Bo Li
Förderung
- Fundamental Research Program of Shanxi Province
- Fundamental Research Program of Shanxi Province under Grant Intelligent Perception and Information Fusion Laboratory
Zitieren
APA
Wang, X., Guo, S., Yang, F., Li, B., & Yan, Y. (2026). Cross-Modal Image Fusion via Structure Preservation and Detail Enhancement Optimization. Sensors, 26(15), 4880. https://doi.org/10.3390/s26154880
Vancouver
Wang X, Guo S, Yang F, Li B, Yan Y. Cross-Modal Image Fusion via Structure Preservation and Detail Enhancement Optimization. Sensors. 2026;26(15):4880. doi:10.3390/s26154880
BibTeX
@article{Wang2026,
author = {Wang, Xiaoxia and Guo, Shuang and Yang, Fengbao and Li, Bo and Yan, Yuhui},
title = {Cross-Modal Image Fusion via Structure Preservation and Detail Enhancement Optimization},
journal = {Sensors},
year = {2026},
volume = {26},
number = {15},
pages = {4880},
doi = {10.3390/s26154880}
}
EUVIMED