解决红外可见光图像融合中光照不足和噪声问题，提升真实场景下的融合效果。
DDFusion:Degradation-Decoupled Fusion Framework for Robust Infrared and Visible Images Fusion
- 分离图像退化成分与有用信息，针对性抑制噪声和低光影响
- 在无损退化处理前提下，融合性能优于现有方法10%以上
- 适合复杂环境下的图像融合任务，如夜间监控、无人机视觉
传统红外与可见光图像融合（IVIF）方法通常假设输入图像质量良好，忽略了真实场景中常见的低光照、噪声等退化问题，限制了其实际应用。为此，我们提出一种退化解耦融合框架（DDFusion），实现退化成分的解耦，并统一建模退化抑制与图像融合。具体地，退化解耦优化网络（DDON）进行特定退化分解，分离出退化相关与退化信息成分，并通过成分专属提取路径实现有效退化抑制与信息特征增强。交互式局部-全局融合网络（ILGFN）在多尺度路径间聚合互补特征，缓解退化优化与融合过程间的解耦带来的性能下降。大量实验表明，DDFusion在清洁与退化条件下均取得更优融合效果。代码已开源：https://github.com/Lmmh058/DDFusion。
原文摘要 · Abstract (English)
Conventional infrared and visible image fusion(IVIF) methods often assume high-quality inputs, neglecting real-world degradations such as low-light and noise, which limits their practical applicability. To address this, we propose a Degradation-Decoupled Fusion(DDFusion) framework, which achieves degradation decoupling and jointly models degradation suppression and image fusion in a unified manner. Specifically, the Degradation-Decoupled Optimization Network(DDON) performs degradation-specific decomposition to decouple inter-degradation and degradation-information components, followed by component-specific extraction paths for effective suppression of degradation and enhancement of informative features. The Interactive Local-Global Fusion Network (ILGFN) aggregates complementary features across multi-scale pathways and alleviates performance degradation caused by the decoupling between degradation optimization and image fusion. Extensive experiments demonstrate that DDFusion achieves superior fusion performance under both clean and degraded conditions. Our code is available at https://github.com/Lmmh058/DDFusion.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。