ReCoFuse：基于复原式多模态扩散互耦的超鲁棒图像融合
ReCoFuse: Ultra-Robust Image Fusion via Restorative Multi-Modal Diffusion Reciprocal Coupling
把扩散采样过程当作多模态复原先验的载体，在每个采样时间步插入跨模态整合模块并把聚合变量回灌到各复原分支，这种「复原-融合互促」的耦合结构可直接迁移到多传感器融合、低质图像增强等需要同时去退化与信息整合的任务。
原文依据 time-aware cross-modal integration modules (TIM) are introduced as a bridge to couple restoration and integration, embedded at each DiM sampling timestep
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论现有遵循一体化硬回归或解耦优化范式的方法在复杂退化条件下融合性能有限。针对这些范式层面的缺陷，本文提出 ReCoFuse，一个基于复原式多模态扩散互耦的超鲁棒图像融合框架。ReCoFuse 重新定义了信息复原与信息整合之间的关系，通过二者的相互增强推导出一种新的互耦优化范式。该框架首先利用扩散模块（DiM）构建两个复原分支，以捕获模态特定的复原先验；随后引入时间感知跨模态整合模块（TIM）作为连接复原与整合的桥梁，将其嵌入每个 DiM 采样时间步以聚合多模态信息。聚合得到的变量不仅反馈至各复原分支，借助跨模态互补性增强退化去除效果，还生成能够全面表征场景的高质量融合图像。此外，本文设计了交替正则化机制，沿梯度路径迭代优化 DiM 与 TIM，确保复原与整合之间的有效协作。大量实验表明，ReCoFuse 在低光照、雾霾、噪声、低对比度和条纹等挑战性退化条件下取得了最优性能。代码已公开于 https://github.com/HaoZhang1018/ReCoFuse。
英文原文摘要 1489 字符
Existing methods following the integrated hard-regression or decoupling optimization paradigms exhibit limited fusion performance under complex degradations. To address these paradigm-level shortcomings, we propose ReCoFuse, an ultra-robust image fusion framework based on restorative multi-modal diffusion reciprocal coupling. ReCoFuse redefines the relationship between information restoration and integration, deriving a novel reciprocal coupling optimization paradigm through their mutual reinforcement. It first constructs two restoration branches using diffusion modules (DiM) to capture modality-specific restoration priors. Then, time-aware cross-modal integration modules (TIM) are introduced as a bridge to couple restoration and integration, embedded at each DiM sampling timestep to aggregate multi-modal information. The aggregated variable not only feeds back to each restoration branch to enhance degradation removal via cross-modal complementarity, but also generates high-quality fused images that comprehensively represent the scene. Moreover, an alternating regularization mechanism is designed to iteratively optimize DiM and TIM along the gradient path, ensuring effective collaboration between restoration and integration. Extensive experiments show that ReCoFuse achieves state-of-the-art performance under challenging degradations such as low light, haze, noise, low contrast, and stripes. The code is publicly available at https://github.com/HaoZhang1018/ReCoFuse.