Degradation-Robust Fusion: An Efficient Degradation-Aware Diffusion Framework for Multimodal Image Fusion in Arbitrary Degradation Scenarios

Yu Shi; Yu Liu; Zhong-Cheng Wu; Juan Cheng; Huafeng Li; Xun Chen

cs.CVApr 10, 2026

Degradation-Robust Fusion: An Efficient Degradation-Aware Diffusion Framework for Multimodal Image Fusion in Arbitrary Degradation Scenarios

Authors: Yu Shi, Yu Liu, Zhong-Cheng Wu, Juan Cheng, Huafeng Li, Xun Chen

Organizations: Department of Biomedical Engineering, Hefei University of Technology · Faculty of Information Engineering and Automation, Kunming University of Science and Technology · School of Information Science and Technology, University of Science and Technology of China

Abstract

Complex degradations like noise, blur, and low resolution are typical challenges in real world image fusion tasks, limiting the performance and practicality of existing methods. End to end neural network based approaches are generally simple to design and highly efficient in inference, but their black-box nature leads to limited interpretability. Diffusion based methods alleviate this to some extent by providing powerful generative priors and a more structured inference process. However, they are trained to learn a single domain target distribution, whereas fusion lacks natural fused data and relies on modeling complementary information from multiple sources, making diffusion hard to apply directly in practice. To address these challenges, this paper proposes an efficient degradation aware diffusion framework for image fusion under arbitrary degradation scenarios. Specifically, instead of explicitly predicting noise as in conventional diffusion models, our method performs implicit denoising by directly regressing the fused image, enabling flexible adaptation to diverse fusion tasks under complex degradations with limited steps. Moreover, we design a joint observation model correction mechanism that simultaneously imposes degradation and fusion constraints during sampling to ensure high reconstruction accuracy. Experiments on diverse fusion tasks and degradation configurations demonstrate the superiority of the proposed method under complex degradation scenarios.

Figures & tables

Figure 1: Comparison of fusion strategies under different degradation scenarios: (a) methods based on neural networks; (b) existing diffusion-based methods; (c) the proposed degradation-aware diffusion framework from this work.

Figure 2: The proposed framework for multimodal image fusion under various degradation scenarios in this work.

Figure 3: Qualitative results of different fusion methods on M3FD dataset. For the comparison methods, we first use corresponding restoration algorithms (e.g., denoising, deblurring, super-resolution) to restore the images, and then apply the respective fusion methods. The proposed method directly reconstructs the fusion results from the degraded source images. In the third degradation scenario, the infrared image is of low resolution and we have enlarged it, the original image is shown in the top-left corner.

Methods	Noise						Blur						Composite degradation
Methods	$Q_{MI}$	$Q_{NCIE}$	$Q^{AB/F}$	$Q_{P}$	$Q_{CB}$	$Q_{W}$	$Q_{MI}$	$Q_{NCIE}$	$Q^{AB/F}$	$Q_{P}$	$Q_{CB}$	$Q_{W}$	$Q_{MI}$	$Q_{NCIE}$	$Q^{AB/F}$	$Q_{P}$	$Q_{CB}$	$Q_{W}$
IFCNN	0.2205	0.8036	0.4056	0.2115	0.4015	0.7778	0.3378	0.8051	0.1042	0.1057	0.3491	0.4969	0.3176	0.8048	0.0965	0.0571	0.3635	0.4708
U2Fusion	0.2454	0.8039	0.4281	0.1817	0.4804	0.7272	0.2891	0.8045	0.1389	0.0696	0.4205	0.5035	0.2817	0.8044	0.1215	0.0491	0.4401	0.5507
MURF	0.2270	0.8038	0.2630	0.0975	0.4383	0.5907	0.3335	0.8054	0.1413	0.0793	0.3966	0.4607	0.3100	0.8050	0.1159	0.0416	0.4093	0.4817
DDFM	0.2685	0.8043	0.3631	0.1543	0.4530	0.7747	0.3320	0.8054	0.1022	0.0631	0.3277	0.4224	0.3202	0.8052	0.0885	0.0488	0.3488	0.4443
Text-DiFuse	0.2896	0.8044	0.2109	0.0576	0.3807	0.3402	0.2905	0.8044	0.1195	0.0493	0.3350	0.2589	0.2929	0.8044	0.1103	0.0462	0.3381	0.2928

Table 1: Objective fusion metrics of various methods under different degradation scenarios on the M3FD dataset (Bold and gray background: best result in each column; underline: second best).

Figure 4: Qualitative comparison of different fusion methods on the Harvard dataset. For the comparison methods, we first apply the corresponding restoration algorithms (e.g., denoising, deblurring, super-resolution) to process the images, and then perform fusion. The proposed method directly reconstructs the fusion results from the degraded source images. In the third degradation scenario, the PET image is of low resolution and we have enlarged it, the original image is shown in the top-left corner.

Methods	Noise						Blur						Composite degradation
Methods	$Q_{MI}$	$Q_{NCIE}$	$Q^{AB/F}$	$Q_{P}$	$Q_{CB}$	$Q_{W}$	$Q_{MI}$	$Q_{NCIE}$	$Q^{AB/F}$	$Q_{P}$	$Q_{CB}$	$Q_{W}$	$Q_{MI}$	$Q_{NCIE}$	$Q^{AB/F}$	$Q_{P}$	$Q_{CB}$	$Q_{W}$
IFCNN	0.5164	0.8067	0.3902	0.1791	0.4611	0.7615	0.6472	0.8073	0.2692	0.1613	0.5891	0.6752	0.5231	0.8065	0.1853	0.0515	0.4613	0.5999
U2Fusion	0.5830	0.8069	0.3379	0.1658	0.4095	0.6827	0.6505	0.8074	0.2373	0.1523	0.3587	0.5760	0.5601	0.8067	0.1761	0.0628	0.4451	0.5374
MURF	0.4456	0.8061	0.3199	0.1380	0.3484	0.6431	0.6061	0.8072	0.3003	0.1273	0.3615	0.6936	0.4349	0.8059	0.1771	0.0447	0.3757	0.5462
DDFM	0.6025	0.8075	0.3840	0.1908	0.6078	0.7532	0.6653	0.8077	0.2507	0.1690	0.5810	0.6208	0.6353	0.8071	0.1971	0.0715	0.5878	0.6032
Text-DiFuse	0.5324	0.8074	0.4026	0.1916	0.2982	0.6810	0.5547	0.8073	0.2839	0.1215	0.3256	0.5820	0.5382	0.8073	0.1810	0.0773	0.2458	0.4893

Table 2: Objective fusion metrics of various methods under different degradation scenarios on the Harvard dataset (Bold and gray background: best result in each column; underline: second best).

Figure 5: Comparison of time efficiency and model parameters across different fusion methods.

Panel of Figure 6 — Figure 6: Ablation study results on two datasets. (a) represents the M3FD dataset, and (b) represents the Harvard dataset.

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 7: Results with and without the joint constraint correction mechanism under different degradation scenarios on M3FD dataset.

Figure 8: Results with and without the joint constraint correction mechanism under different degradation scenarios on PET-MRI dataset.

	M3FD						PET-MRI
	Noise		Blur		Composite degradation		Noise		Blur		Composite degradation
Metrics	Ours	w/o constraint	Ours	w/o constraint	Ours	w/o constraint	Ours	w/o constraint	Ours	w/o constraint	Ours	w/o constraint
$Q_{MI}$	0.3505	0.3322	0.4477	0.4140	0.3732	0.2322	0.6171	0.6185	0.6469	0.6318	0.6019	0.6116
$Q_{NCIE}$	0.8052	0.8050	0.8068	0.8062	0.8055	0.8038	0.8078	0.8077	0.8077	0.8071	0.8073	0.8074
$Q^{AB/F}$	0.4083	0.3759	0.3698	0.3233	0.2199	0.1054	0.4258	0.4092	0.3855	0.2019	0.2956	0.2544
$Q_{P}$	0.1825	0.1454	0.1671	0.1409	0.0755	0.0449	0.2436	0.2336	0.2016	0.1199	0.1258	0.1196

Appendix

Table 3: Ablation results for M3FD and PET-MRI datasets under different degradation scenarios. The best values for each metric are highlighted in light gray.

Figure 9: Qualitative detection results based on fusion images generated by different fusion methods.

Method	Precision	Recall	[email protected]
IFCNN	0.9396	0.7933	0.8906
U2Fusion	0.9273	0.7605	0.8700
MURF	0.9510	0.7942	0.8865
DDFM	0.9620	0.7062	0.8509
Text-Difuse	0.9723	0.6546	0.8172
VDMUFusion	0.9690	0.7042	0.8499

Appendix

Table 4: Detection performance comparison on M3FD dataset.

Metrics	$T=1$	$T=2$	$T=3$ (Ours)	$T=4$	$T=5$
$Q_{MI}$	0.3577	0.3721	0.3732	0.3717	0.3663
$Q_{NCIE}$	0.8053	0.8055	0.8055	0.8047	0.8065
$Q^{AB/F}$	0.2061	0.2184	0.2199	0.2187	0.2185
$Q_{P}$	0.0618	0.0660	0.0755	0.0693	0.0689
$Q_{CB}$	0.3216	0.3587	0.3790	0.3768	0.3673
$Q_{W}$	0.6192	0.6221	0.6237	0.6178	0.6133

Appendix

Table 5: Quantitative comparison of different

T

values.

Explore similar work

UniDiffFusion: A Unified Diffusion Framework for Multi-Task and Degradation-Robust Image Fusion
Aug 22, 2026Xingxin Xu, Siqi Zhao, Xin Li +3Multi-Source Image Fusion Infrared-Visible Image Fusion
School of New Media and Communication, Tianjin University · School of Artificial Intelligence, Tianjin University · School of Automation, Southeast University +1
Diff-RF: Mutually Reinforced Image Registration and Fusion via Degradation-Aware Learning
Sep 23, 2026Xunpeng Yi, Zaixi Du, Qinglong Yan +3Multi-Source Image Fusion Cross-Modal Image Registration
Electronic Information School, Wuhan University, Wuhan 430072, China
Unleashing the Power of Text: Text-Guided Flow Matching for Image Fusion under Complex Degradations
Aug 1, 2026Axi Niu, Jieheng Li, Kang Zhang +3Flow Matching Multi-Source Image Fusion
School of Computer Science, Northwestern Polytechnical University, Xi'an, China · School of Computer Science, Northwestern Polytechnical University, Xi’an, Shaanxi, China · School of Electrical Engineering, KAIST, Daejeon, Republic of Korea +2

Aug 22, 2026J/K move · Enter open · S save

UniDiffFusion: A Unified Diffusion Framework for Multi-Task and Degradation-Robust Image Fusion

Xingxin Xu, Siqi Zhao, Xin Li, Xinjie Yao+2

School of New Media and Communication, Tianjin University · School of Artificial Intelligence, Tianjin University · School of Automation, Southeast University+1

Multi-Source Image Fusion Infrared-Visible Image Fusion Multimodal Fusion

Open paper AskPDF arXiv

General image fusion aims to integrate complementary information from multiple source images, but existing methods often rely on task-specific models and struggle to maintain robust performance under diverse degradation conditions. In this paper, we propose UniDiffFusion, a unified diffusion framework for multi-task and degradation-robust image fusion. UniDiffFusion leverages the strong generative prior of a pretrained diffusion model to establish a shared fusion backbone across heterogeneous fusion tasks, while introducing task- and degradation-aware conditional adaptation to accommodate their distinct information-selection requirements. Specifically, we employ task prompt modulation to progressively adapt the shared diffusion representations to different fusion objectives, and develop a degradation prompt router to dynamically retrieve degradation-aware priors and restore corrupted source features before fusion. Furthermore, an application prompt bank is introduced to incorporate task-oriented semantic guidance for downstream applications, such as object detection and semantic segmentation, without altering the shared fusion and restoration pathways. The proposed framework is trained in a progressive manner to decouple fusion learning, degradation-aware restoration, and application-specific adaptation, thereby reducing interference among heterogeneous objectives. Extensive experiments on visible-infrared, multi-exposure, and multi-focus image fusion demonstrate that UniDiffFusion achieves superior fusion quality and robustness under both clean and degraded conditions. Moreover, UniDiffFusion consistently improves downstream detection and semantic segmentation performance, demonstrating its effectiveness as a unified diffusion framework for both perceptual fusion and task-oriented vision.

Abstract

Explore similar work

UniDiffFusion: A Unified Diffusion Framework for Multi-Task and Degradation-Robust Image Fusion

Diff-RF: Mutually Reinforced Image Registration and Fusion via Degradation-Aware Learning

Unleashing the Power of Text: Text-Guided Flow Matching for Image Fusion under Complex Degradations