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

• URL: http://arxiv.org/abs/2608.25274v1
• Date: Wed, 26 Aug 2026 01:20:46 GMT
• Title: OpenCVL: An Open, Diverse, and Large-Scale Dataset for Fine-Grained Cross-View Localization
• Abstract summary: We introduce OpenCVL, a large-scale, diverse, and open dataset containing 617,388 ground-aerial image pairs spanning 41 cities across four European countries.<n>OpenCVL includes dedicated cross-area and snowy test sets to assess generalization and robustness.<n>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.
• Score: 73.84434300039767
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Accuracy potential of visual localization exploiting high-end street-level imagery [2.9538906120661186]
  We introduce a scalable visual localization pipeline that employs precisely georeferenced, high-resolution imagery directly asfrom-the-fly local scene representation.<n>Experiments demonstrate median pose accuracies in the range of 1-5 cm for translation and 0.05-0.1 for rotation, reaching as low as 1 cm under survey-grade conditions.
  arXiv  Detail & Related papers  (2026-07-27T13:25:31Z)
• Beyond Matching to Tiles: Bridging Unaligned Aerial and Satellite Views for Vision-Only UAV Navigation [51.286599397552756]
  We present Bearing-UAV, a vision-driven cross-view navigation method that jointly predicts UAV absolute location and heading from neighboring features.<n>We also present Bearing-UAV-90k, a benchmark for evaluating cross-view localization and navigation.
  arXiv  Detail & Related papers  (2026-03-23T16:17:39Z)
• OrthoLoC: UAV 6-DoF Localization and Calibration Using Orthographic Geodata [45.03897051444244]
  We propose OrthoLoC, the first large-scale dataset comprising 16,425 UAV images from Germany and the United States with multiple modalities.<n>The dataset addresses domain shifts between UAV imagery and geospatial data.<n>We introduce a refinement technique called AdHoP, which can be integrated with any feature matcher, improving matching by up to 95% and reducing translation error by up to 63%.
  arXiv  Detail & Related papers  (2025-09-22T19:22:32Z)
• Loc$^2$: Interpretable Cross-View Localization via Depth-Lifted Local Feature Matching [80.57282092735991]
  We propose an accurate and interpretable fine-grained cross-view localization method.<n>It estimates the 3 Degrees of Freedom (DoF) pose of a ground-level image by matching its local features with a reference aerial image.<n> Experiments show state-of-the-art accuracy in challenging scenarios such as cross-area testing and unknown orientation.
  arXiv  Detail & Related papers  (2025-09-11T18:52:16Z)
• Zooming In on Fakes: A Novel Dataset for Localized AI-Generated Image Detection with Forgery Amplification Approach [69.01456182499486]
  textbfBR-Gen is a large-scale dataset of 150,000 locally forged images with diverse scene-aware annotations.<n>textbfNFA-ViT is a Noise-guided Forgery Amplification Vision Transformer that enhances the detection of localized forgeries.
  arXiv  Detail & Related papers  (2025-04-16T09:57:23Z)
• Exploring the best way for UAV visual localization under Low-altitude Multi-view Observation Condition: a Benchmark [6.693781685584959]
  Low-altitude, Multi-view UAV AVL presents greater challenges due to extreme viewpoint changes.<n>This benchmark revealed the challenges of Low-altitude, Multi-view UAV AVL and provided valuable guidance for future research.
  arXiv  Detail & Related papers  (2025-03-12T03:29:27Z)
• Cross-View Image Set Geo-Localization [29.13525096798705]
  Cross-view geo-localization (CVGL) has been widely applied in fields such as robotic navigation and augmented reality.<n>We propose a novel task: Cross-View Image Set Geo-Localization (Set-CVGL), which gathers multiple images with diverse perspectives as a query set for localization.
  arXiv  Detail & Related papers  (2024-12-25T09:46:14Z)
• Contrasting Deepfakes Diffusion via Contrastive Learning and Global-Local Similarities [88.398085358514]
  Contrastive Deepfake Embeddings (CoDE) is a novel embedding space specifically designed for deepfake detection. CoDE is trained via contrastive learning by additionally enforcing global-local similarities.
  arXiv  Detail & Related papers  (2024-07-29T18:00:10Z)
• CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representations [90.50864830038202]
  We present Contrastive Spatial Pre-Training (CSP), a self-supervised learning framework for geo-tagged images. We use a dual-encoder to separately encode the images and their corresponding geo-locations, and use contrastive objectives to learn effective location representations from images. CSP significantly boosts the model performance with 10-34% relative improvement with various labeled training data sampling ratios.
  arXiv  Detail & Related papers  (2023-05-01T23:11:18Z)
• AiRound and CV-BrCT: Novel Multi-View Datasets for Scene Classification [2.931113769364182]
  We present two new publicly available datasets named thedatasetand CV-BrCT. The first one contains triplets of images from the same geographic coordinate with different perspectives of view extracted from various places around the world. The second dataset contains pairs of aerial and street-level images extracted from southeast Brazil.
  arXiv  Detail & Related papers  (2020-08-03T18:55:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.