发表机构
École Polytechnique Fédérale de Lausanne (EPFL); Southern University of Science and Technology (SUSTech); Delft University of Technology; Zenseact（洛桑联邦理工学院; 南方科技大学; 代尔夫特理工大学; Zenseact公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有CVL数据集的多样性与可扩展性不足问题，本文构建了含617388组图像对的OpenCVL数据集，开发数据整理框架处理野外数据，实验证实融入有噪声野外数据可提升CVL模型性能。
AI 中文摘要
细粒度跨视角定位（Cross-View Localization, CVL）通过将地面图像与地理参考的航拍图像对齐，来估计地面图像的精确位置和方向，为具有挑战性的城市环境中的全球导航卫星系统（Global Navigation Satellite Systems, GNSS）提供了一种可扩展的替代方案。现有数据集依赖于高端传感器套件采集的数据，这固有地限制了图像的多样性和可扩展性。尽管野外图像数量丰富，但它们的地理标签存在噪声，无法用于可靠评估。为了弥合这一差距，我们引入了OpenCVL，这是一个包含617388组地面-航拍图像对的大规模、多样且开放的数据集，覆盖了四个欧洲国家的41个城市。所有图像均来自许可平台，确保了长期可访问性，并支持开放和可复现的研究。训练集结合了高端传感器采集的图像与多样的野外图像。我们进一步开发了一个数据整理框架，该框架对姿态注释进行过滤和校正，以构建可靠的野外评估数据。此外，OpenCVL还包含专门的跨区域和积雪测试集，用于评估模型的泛化能力和鲁棒性。在OpenCVL上对最先进的CVL模型进行的实验表明，融入有噪声的野外数据可持续提升在干净测试集上的性能，这为利用多样的真实世界图像扩展CVL提供了一个有前景的方向。
英文摘要
Fine-grained Cross-View Localization (CVL) estimates the precise position and orientation of a ground-level image by aligning it with geo-referenced aerial imagery, offering a scalable alternative to Global Navigation Satellite Systems (GNSS) in challenging urban environments. Existing datasets rely on data collected with high-end sensor suites, which inherently limit image diversity and scalability. While in-the-wild images are abundant, their noisy geo-tags make them unsuitable for reliable evaluation. To bridge this gap, we introduce OpenCVL, a large-scale, diverse, and open dataset containing 617,388 ground-aerial image pairs spanning 41 cities across four European countries. All images are sourced from permissive platforms, ensuring long-term accessibility and supporting open and reproducible research. The training set combines images captured with high-end sensors with diverse in-the-wild imagery. We further develop a data curation framework that filters and corrects pose annotations to construct reliable in-the-wild evaluation data. In addition, OpenCVL includes dedicated cross-area and snowy test sets to assess generalization and robustness. Experiments with a state-of-the-art CVL model on OpenCVL show that incorporating noisy in-the-wild data consistently improves performance on clean test sets, suggesting a promising direction for scaling CVL with diverse real-world imagery.
