退化鲁棒融合：一种用于任意退化场景下多模态图像融合的高效退化感知扩散框架
Degradation-Robust Fusion: An Efficient Degradation-Aware Diffusion Framework for Multimodal Image Fusion in Arbitrary Degradation Scenarios
提出一种隐式去噪的扩散框架，通过直接回归融合图像而非预测噪声，并设计联合观测模型校正机制在采样中同时施加退化与融合约束，可复用于任意退化场景下的多模态图像融合任务。
原文依据 our method performs implicit denoising by directly regressing the fused image
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论噪声、模糊和低分辨率等复杂退化是真实世界图像融合任务中的典型挑战，限制了现有方法的性能与实用性。基于端到端神经网络的方法通常设计简单且推理高效，但其黑盒特性导致可解释性有限。基于扩散的方法通过提供强大的生成先验和更结构化的推理过程，在一定程度上缓解了这一问题。然而，它们被训练来学习单一域的目标分布，而融合任务缺乏自然的融合数据，依赖于对多源互补信息的建模，这使得扩散模型难以直接应用于实践。为解决这些挑战，本文提出了一种用于任意退化场景下图像融合的高效退化感知扩散框架。具体而言，不同于传统扩散模型中显式预测噪声，我们的方法通过直接回归融合图像来执行隐式去噪，从而能够在有限步数内灵活适应复杂退化下的多样融合任务。此外，我们设计了一种联合观测模型校正机制，在采样过程中同时施加退化约束和融合约束，以确保高重建精度。在多种融合任务和退化配置上的实验证明了所提方法在复杂退化场景下的优越性。代码：https://github.com/YShi-cool/DRFusion。
英文原文摘要 1531 字符
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. Code: https://github.com/YShi-cool/DRFusion.