OpenCVL: An Open, Diverse, and Large-Scale Dataset for Fine-Grained Cross-View Localization

2026-08-25

AI Summary

为了解决城市环境中精细跨视角定位问题，本文通过构建大规模、多样化的OpenCVL数据集，并开发数据管理框架来过滤和修正姿态注释，从而提高模型性能。

Abstract

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.

Problem

• Cross-View Localization
• image diversity
• scalability
• geo-tags
• evaluation

Innovation

• large-scale dataset
• diverse imagery
• data curation framework
• cross-view localization
• generalization and robustness