双曲循环对齐用于红外-可见图像融合
Hyperbolic Cycle Alignment for Infrared-Visible Image Fusion
AI总结：
本文提出基于双曲空间的双曲循环对齐网络，通过双路径交叉模态循环对齐框架和双曲层次对比对齐模块，实现更有效的多模态图像对齐与融合。
摘要：
图像融合合成来自多个源的互补信息，以缓解单模态成像系统的固有局限。准确的图像配准对于有效的多源数据融合至关重要。然而，现有的配准方法通常基于欧几里得空间中的图像平移，无法有效处理跨模态不对齐，导致配准和融合质量不佳。为克服这一限制，我们探索非欧几里得空间中的图像对齐，并提出双曲循环对齐网络（Hy-CycleAlign）。到目前为止，Hy-CycleAlign是首个基于双曲空间的图像配准方法。它引入了双路径交叉模态循环配准框架，在其中前向配准网络对齐跨模态输入，而后向配准网络重建原始图像，形成具有几何一致性的闭环配准结构。此外，我们设计了双曲层次对比对齐（H$^{2}$CA）模块，将图像映射到双曲空间并施加配准约束，有效减少由模态差异引起的干扰。我们进一步分析了欧几里得和双曲空间中的图像配准，证明双曲空间能够实现更敏感和有效的多模态图像配准。在对齐多模态图像的大量实验中，我们的方法在图像对齐和融合方面显著优于现有方法。我们的代码将公开发布。
英文摘要：
Image fusion synthesizes complementary information from multiple sources, mitigating the inherent limitations of unimodal imaging systems. Accurate image registration is essential for effective multi-source data fusion. However, existing registration methods, often based on image translation in Euclidean space, fail to handle cross-modal misalignment effectively, resulting in suboptimal alignment and fusion quality. To overcome this limitation, we explore image alignment in non-Euclidean space and propose a Hyperbolic Cycle Alignment Network (Hy-CycleAlign). To the best of our knowledge, Hy-CycleAlign is the first image registration method based on hyperbolic space. It introduces a dual-path cross-modal cyclic registration framework, in which a forward registration network aligns cross-modal inputs, while a backward registration network reconstructs the original image, forming a closed-loop registration structure with geometric consistency. Additionally, we design a Hyperbolic Hierarchy Contrastive Alignment (H$^{2}$CA) module, which maps images into hyperbolic space and imposes registration constraints, effectively reducing interference caused by modality discrepancies. We further analyze image registration in both Euclidean and hyperbolic spaces, demonstrating that hyperbolic space enables more sensitive and effective multi-modal image registration. Extensive experiments on misaligned multi-modal images demonstrate that our method significantly outperforms existing approaches in both image alignment and fusion. Our code will be publicly available.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
