VIRD：通过双轴变换构造视角不变表征用于跨视角姿态估计
VIRD: View-Invariant Representation through Dual-Axis Transformation for Cross-View Pose Estimation
用极坐标变换把卫星图与地面图的水平对应关系对齐，再用上下文增强的位置注意力缓解垂直错位，这套「双轴变换构造视角不变表征」的思路可直接迁移到任何跨视角匹配/定位任务（如无人机-卫星、地面-航拍检索）。
原文依据 VIRD first applies a polar transformation to the satellite view to facilitate horizontal correspondence
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论精确的全局定位对自动驾驶与机器人至关重要，但基于 GNSS 的方法常因遮挡和多径效应而性能下降。作为一种新兴替代方案，跨视角姿态估计以带地理参考的卫星图像为参照，预测地面视角图像对应的三自由度相机姿态。然而，现有方法难以弥合地面视角与卫星视角之间巨大的视角差异，主要原因是空间对应关系有限。我们提出一种新的跨视角姿态估计方法，通过双轴变换构造视角不变表征（VIRD）。VIRD 首先对卫星视角施加极坐标变换以促进水平方向的对应，随后在地面特征与极坐标变换后的卫星特征上使用上下文增强的位置注意力以缓解垂直方向错位，从而显式地弥合视角差异。为进一步增强视角不变性，我们引入视图重建损失，促使所导出的表征能够重建原始图像与跨视角图像。在 KITTI 和 VIGOR 数据集上的实验表明，VIRD 在无朝向先验条件下优于最优方法，在 KITTI 上将位置与朝向误差中位数分别降低 50.7% 和 76.5%，在 VIGOR 上分别降低 18.0% 和 46.8%。
英文原文摘要 1344 字符
Accurate global localization is critical for autonomous driving and robotics, but GNSS-based approaches often degrade due to occlusion and multipath effects. As an emerging alternative, cross-view pose estimation predicts the 3-DoF camera pose corresponding to a ground-view image with respect to a geo-referenced satellite image. However, existing methods struggle to bridge the significant viewpoint gap between the ground and satellite views mainly due to limited spatial correspondences. We propose a novel cross-view pose estimation method that constructs view-invariant representations through dual-axis transformation (VIRD). VIRD first applies a polar transformation to the satellite view to facilitate horizontal correspondence, then uses context-enhanced positional attention on the ground and polar-transformed satellite features to mitigate vertical misalignment, explicitly bridging the viewpoint gap. To further strengthen view invariance, we introduce a view-reconstruction loss that encourages the derived representations to reconstruct the original and cross-view images. Experiments on the KITTI and VIGOR datasets demonstrate that VIRD outperforms the state-of-the-art methods without orientation priors, reducing median position and orientation errors by 50.7% and 76.5% on KITTI, and 18.0% and 46.8% on VIGOR, respectively.