Dual-Domain Perspective on Degradation-Aware Fusion: A VLM-Guided Robust Infrared and Visible Image Fusion Framework

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Tianpei, Zhao, Jufeng, Zhu, Yiming, Cui, Guangmang
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916935699005440
author Zhang, Tianpei
Zhao, Jufeng
Zhu, Yiming
Cui, Guangmang
author_facet Zhang, Tianpei
Zhao, Jufeng
Zhu, Yiming
Cui, Guangmang
contents Most existing infrared-visible image fusion (IVIF) methods assume high-quality inputs, and therefore struggle to handle dual-source degraded scenarios, typically requiring manual selection and sequential application of multiple pre-enhancement steps. This decoupled pre-enhancement-to-fusion pipeline inevitably leads to error accumulation and performance degradation. To overcome these limitations, we propose Guided Dual-Domain Fusion (GD^2Fusion), a novel framework that synergistically integrates vision-language models (VLMs) for degradation perception with dual-domain (frequency/spatial) joint optimization. Concretely, the designed Guided Frequency Modality-Specific Extraction (GFMSE) module performs frequency-domain degradation perception and suppression and discriminatively extracts fusion-relevant sub-band features. Meanwhile, the Guided Spatial Modality-Aggregated Fusion (GSMAF) module carries out cross-modal degradation filtering and adaptive multi-source feature aggregation in the spatial domain to enhance modality complementarity and structural consistency. Extensive qualitative and quantitative experiments demonstrate that GD^2Fusion achieves superior fusion performance compared with existing algorithms and strategies in dual-source degraded scenarios. The code will be publicly released after acceptance of this paper.
format Preprint
id arxiv_https___arxiv_org_abs_2509_05000
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Dual-Domain Perspective on Degradation-Aware Fusion: A VLM-Guided Robust Infrared and Visible Image Fusion Framework
Zhang, Tianpei
Zhao, Jufeng
Zhu, Yiming
Cui, Guangmang
Computer Vision and Pattern Recognition
Most existing infrared-visible image fusion (IVIF) methods assume high-quality inputs, and therefore struggle to handle dual-source degraded scenarios, typically requiring manual selection and sequential application of multiple pre-enhancement steps. This decoupled pre-enhancement-to-fusion pipeline inevitably leads to error accumulation and performance degradation. To overcome these limitations, we propose Guided Dual-Domain Fusion (GD^2Fusion), a novel framework that synergistically integrates vision-language models (VLMs) for degradation perception with dual-domain (frequency/spatial) joint optimization. Concretely, the designed Guided Frequency Modality-Specific Extraction (GFMSE) module performs frequency-domain degradation perception and suppression and discriminatively extracts fusion-relevant sub-band features. Meanwhile, the Guided Spatial Modality-Aggregated Fusion (GSMAF) module carries out cross-modal degradation filtering and adaptive multi-source feature aggregation in the spatial domain to enhance modality complementarity and structural consistency. Extensive qualitative and quantitative experiments demonstrate that GD^2Fusion achieves superior fusion performance compared with existing algorithms and strategies in dual-source degraded scenarios. The code will be publicly released after acceptance of this paper.
title Dual-Domain Perspective on Degradation-Aware Fusion: A VLM-Guided Robust Infrared and Visible Image Fusion Framework
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.05000