CRFT：用于跨模态图像配准的一致性循环特征流Transformer
CRFT: Consistent-Recurrent Feature Flow Transformer for Cross-Modal Image Registration
提出基于特征流学习的统一粗到细跨模态配准框架，其迭代差异引导注意力与空间几何变换循环细化流场的设计，可复用于多模态空间对应任务（如遥感、医学影像配准），为处理大仿射和尺度变化下的对齐提供可借鉴的Transformer架构。
原文依据 CRFT learns a modality-independent feature flow representation within a transformer-based architecture that jointly performs feature alignment and flow estimation.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们提出一致性循环特征流Transformer（CRFT），一种基于特征流学习的统一粗到细框架，用于鲁棒的跨模态图像配准。CRFT在基于Transformer的架构中学习模态无关的特征流表示，该架构联合执行特征对齐和流估计。粗阶段通过多尺度特征相关建立全局对应关系，而细阶段通过分层特征融合和自适应空间推理细化局部细节。为增强几何适应性，一种带有空间几何变换（SGT）的迭代差异引导注意力机制循环细化流场，逐步捕捉细微的空间不一致性并强制特征级一致性。该设计能够在大仿射和尺度变化下实现精确对齐，同时保持跨模态的结构连贯性。在不同跨模态数据集上的大量实验表明，CRFT在准确性和鲁棒性上均持续优于最优的配准方法。除配准外，CRFT为多模态空间对应提供了一种可推广的范式，在遥感、自主导航和医学成像中具有广泛适用性。代码和数据集已公开于https://github.com/NEU-Liuxuecong/CRFT。
英文原文摘要 1381 字符
We present Consistent-Recurrent Feature Flow Transformer (CRFT), a unified coarse-to-fine framework based on feature flow learning for robust cross-modal image registration. CRFT learns a modality-independent feature flow representation within a transformer-based architecture that jointly performs feature alignment and flow estimation. The coarse stage establishes global correspondences through multi-scale feature correlation, while the fine stage refines local details via hierarchical feature fusion and adaptive spatial reasoning. To enhance geometric adaptability, an iterative discrepancy-guided attention mechanism with a Spatial Geometric Transform (SGT) recurrently refines the flow field, progressively capturing subtle spatial inconsistencies and enforcing feature-level consistency. This design enables accurate alignment under large affine and scale variations while maintaining structural coherence across modalities. Extensive experiments on diverse cross-modal datasets demonstrate that CRFT consistently outperforms state-of-the-art registration methods in both accuracy and robustness. Beyond registration, CRFT provides a generalizable paradigm for multimodal spatial correspondence, offering broad applicability to remote sensing, autonomous navigation, and medical imaging. Code and datasets are publicly available at https://github.com/NEU-Liuxuecong/CRFT.