LoD-Loc v2：基于显式轮廓对齐的低细节层次城市模型空中视觉定位
LoD-Loc v2: Aerial Visual Localization over Low Level-of-Detail City Models using Explicit Silhouette Alignment
AI总结：
LoD-Loc v2 提出基于显式轮廓对齐的由粗到精定位方法，首次在低细节层次城市模型上实现无人机空中视觉定位，并发布相关数据集，性能大幅超越现有基线。
摘要：
我们提出了一种在低细节层次（LoD）城市模型上进行空中视觉定位的新方法。此前基于线框对齐的方法 LoD-Loc 已展示出利用 LoD 模型实现良好定位效果的能力。然而，LoD-Loc 主要依赖高 LoD（LoD3 或 LoD2）城市模型，但现有可用模型以及许多国家计划在全国范围内构建的模型大多为低 LoD（LoD1）。因此，在低 LoD 城市模型上实现定位有望释放无人机在全球城市定位中的潜力。为解决这些问题，我们提出 LoD-Loc v2，该方法采用由粗到精的策略，利用显式轮廓对齐在空中实现对低 LoD 城市模型的精确定位。具体而言，给定一张查询图像，LoD-Loc v2 首先应用建筑物分割网络来提取建筑物轮廓。随后，在粗略位姿选择阶段，我们通过在先验位姿周围均匀采样位姿假设来构建位姿代价体，以表示位姿概率分布。代价体中的每个代价值衡量投影轮廓与预测轮廓之间的对齐程度。我们选择具有最大代价值的位姿作为粗略位姿。在精细位姿估计阶段，采用结合多波束跟踪方法的粒子滤波技术，高效探索假设空间并获得最终位姿估计。为进一步推动该领域的研究，我们发布了两个包含 LoD1 城市模型的数据集，覆盖 10.7 km² 区域，并提供真实 RGB 查询图像和真值位姿标注。实验结果表明，LoD-Loc v2 在高 LoD 模型上提高了估计精度，并首次实现了在低 LoD 模型上的定位。此外，该方法以大幅优势超越最先进的基线方法，甚至优于基于纹理模型的方法，并扩大了收敛域以容纳更大的先验误差。
英文摘要：
We propose a novel method for aerial visual localization over low Level-of-Detail (LoD) city models. Previous wireframe-alignment-based method LoD-Loc has shown promising localization results leveraging LoD models. However, LoD-Loc mainly relies on high-LoD (LoD3 or LoD2) city models, but the majority of available models and those many countries plan to construct nationwide are low-LoD (LoD1). Consequently, enabling localization on low-LoD city models could unlock drones' potential for global urban localization. To address these issues, we introduce LoD-Loc v2, which employs a coarse-to-fine strategy using explicit silhouette alignment to achieve accurate localization over low-LoD city models in the air. Specifically, given a query image, LoD-Loc v2 first applies a building segmentation network to shape building silhouettes. Then, in the coarse pose selection stage, we construct a pose cost volume by uniformly sampling pose hypotheses around a prior pose to represent the pose probability distribution. Each cost of the volume measures the degree of alignment between the projected and predicted silhouettes. We select the pose with maximum value as the coarse pose. In the fine pose estimation stage, a particle filtering method incorporating a multi-beam tracking approach is used to efficiently explore the hypothesis space and obtain the final pose estimation. To further facilitate research in this field, we release two datasets with LoD1 city models covering 10.7 km , along with real RGB queries and ground-truth pose annotations. Experimental results show that LoD-Loc v2 improves estimation accuracy with high-LoD models and enables localization with low-LoD models for the first time. Moreover, it outperforms state-of-the-art baselines by large margins, even surpassing texture-model-based methods, and broadens the convergence basin to accommodate larger prior errors.
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。
