解耦后对齐：基于跨尺度特征解耦的非迭代混合多模态图像配准
Disentangle-then-Align: Non-Iterative Hybrid Multimodal Image Registration via Cross-Scale Feature Disentanglement
提出跨尺度解耦与自适应投影模块（CDAP）抑制模态私有线索，结合混合参数预测模块（HPPM）实现非迭代的全局刚性参数与形变场联合估计，为多模态配准提供可复用的解耦-对齐框架。
原文依据 we propose HRNet, a Hybrid Registration Network that couples representation disentanglement with hybrid parameter prediction.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论多模态图像配准是一项基础任务，也是下游跨模态分析的前提。尽管近期在共享特征提取和多尺度架构方面取得了进展，但仍存在两个关键局限。首先，一些方法利用解耦来学习共享特征，但主要对共享部分进行正则化，导致模态私有线索泄漏到共享空间中。其次，大多数多尺度框架仅支持单一变换类型，当全局错位与局部形变共存时限制了其适用性。为解决这些问题，我们将混合多模态配准形式化为联合学习稳定的共享特征空间和统一的混合变换。基于这一观点，我们提出了HRNet，一种将表示解耦与混合参数预测相结合的混合配准网络。带有模态特定批量归一化（MSBN）的共享骨干网络提取多尺度特征，而跨尺度解耦与自适应投影（CDAP）模块抑制模态私有线索，并将共享特征投影到稳定子空间以进行匹配。基于该共享空间，混合参数预测模块（HPPM）执行非迭代的由粗到细的全局刚性参数和形变场估计，并将其融合为一致的形变场。在四个多模态数据集上的大量实验表明，在刚性和非刚性配准任务上均达到了最优性能。代码可在项目网站获取。
英文原文摘要 1526 字符
Multimodal image registration is a fundamental task and a prerequisite for downstream cross-modal analysis. Despite recent progress in shared feature extraction and multi-scale architectures, two key limitations remain. First, some methods use disentanglement to learn shared features but mainly regularize the shared part, allowing modality-private cues to leak into the shared space. Second, most multi-scale frameworks support only a single transformation type, limiting their applicability when global misalignment and local deformation coexist. To address these issues, we formulate hybrid multimodal registration as jointly learning a stable shared feature space and a unified hybrid transformation. Based on this view, we propose HRNet, a Hybrid Registration Network that couples representation disentanglement with hybrid parameter prediction. A shared backbone with Modality-Specific Batch Normalization (MSBN) extracts multi-scale features, while a Cross-scale Disentanglement and Adaptive Projection (CDAP) module suppresses modality-private cues and projects shared features into a stable subspace for matching. Built on this shared space, a Hybrid Parameter Prediction Module (HPPM) performs non-iterative coarse-to-fine estimation of global rigid parameters and deformation fields, which are fused into a coherent deformation field. Extensive experiments on four multimodal datasets demonstrate state-of-the-art performance on rigid and non-rigid registration tasks. The code is available at the project website.