GDROS：一种针对大几何变换下光学-SAR图像的几何引导密集配准框架
GDROS: A Geometry-Guided Dense Registration Framework for Optical-SAR Images under Large Geometric Transformations
AI总结：
针对大几何变换下光学与SAR图像配准困难的问题，提出几何引导的密集配准框架GDROS，通过CNN-Transformer提取特征构建4D相关体，并利用最小二乘回归施加仿射变换约束光流场，在多个数据集上显著优于现有方法。
摘要：
光学与合成孔径雷达（SAR）遥感图像的配准是图像融合和视觉导航任务的关键基础。由于模态差异，主要表现为严重的非线性辐射差异（NRD）、几何畸变和噪声变化，该任务极具挑战性。在大几何变换下，现有的基于经典模板和稀疏关键点的策略难以在光学-SAR图像对上实现可靠的配准结果。为了解决这些局限性，我们提出了GDROS，一种利用全局跨模态图像交互的几何引导密集配准框架。首先，我们通过CNN-Transformer混合特征提取模块从光学和SAR图像中提取跨模态深度特征，在此基础上构建多尺度4D相关体并迭代细化，以建立像素级密集对应关系。随后，我们实现了最小二乘回归（LSR）模块，从几何上约束预测的密集光流场。这种几何引导通过将估计的仿射变换直接施加于最终的光流预测上，缓解了预测发散。我们在具有不同空间分辨率的三个代表性数据集WHU-Opt-SAR数据集、OS数据集和UBCv2数据集上进行了大量实验，证明了我们提出的方法在不同成像分辨率下的稳健性能。定性和定量结果表明，GDROS在所有指标上均显著优于当前最先进的方法。我们的源代码将发布于：https://github.com/Zi-Xuan-Sun/GDROS。
英文摘要：
Registration of optical and synthetic aperture radar (SAR) remote sensing images serves as a critical foundation for image fusion and visual navigation tasks. This task is particularly challenging because of their modal discrepancy, primarily manifested as severe nonlinear radiometric differences (NRD), geometric distortions, and noise variations. Under large geometric transformations, existing classical template-based and sparse keypoint-based strategies struggle to achieve reliable registration results for optical-SAR image pairs. To address these limitations, we propose GDROS, a geometry-guided dense registration framework leveraging global cross-modal image interactions. First, we extract cross-modal deep features from optical and SAR images through a CNN-Transformer hybrid feature extraction module, upon which a multi-scale 4D correlation volume is constructed and iteratively refined to establish pixel-wise dense correspondences. Subsequently, we implement a least squares regression (LSR) module to geometrically constrain the predicted dense optical flow field. Such geometry guidance mitigates prediction divergence by directly imposing an estimated affine transformation on the final flow predictions. Extensive experiments have been conducted on three representative datasets WHU-Opt-SAR dataset, OS dataset, and UBCv2 dataset with different spatial resolutions, demonstrating robust performance of our proposed method across different imaging resolutions. Qualitative and quantitative results show that GDROS significantly outperforms current state-of-the-art methods in all metrics. Our source code will be released at: https://github.com/Zi-Xuan-Sun/GDROS.
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。
