mlsanityData to 14 Oct 2026

Danish Airs and Grounds: A Dataset for Aerial-to-Street-Level Place Recognition and Localization

arXiv 2202.01821 ↗First posted 3 Feb 2022cs.CV cs.ROcited by 12

Not on the map. Why?

Abstract (arXiv)

Place recognition and visual localization are particularly challenging in wide baseline configurations. In this paper, we contribute with the Danish Airs and Grounds (DAG) dataset, a large collection of street-level and aerial images targeting such cases. Its main challenge lies in the extreme viewing-angle difference between query and reference images with consequent changes in illumination and perspective. The dataset is larger and more diverse than current publicly available data, including more than 50 km of road in urban, suburban and rural areas. All images are associated with accurate 6-DoF metadata that allows the benchmarking of visual localization methods. We also propose a map-to-image re-localization pipeline, that first estimates a dense 3D reconstruction from the aerial images and then matches query street-level images to street-level renderings of the 3D model. The dataset can be downloaded at: https://frederikwarburg.github.io/DAG

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 21 of its 50 references that are in the map. First posted on arXiv 3 Feb 2022.

Builds on

21 of 50 references.

References · 21

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,320
  3. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 984
  4. 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 941
  5. 2018From Coarse to Fine: Robust Hierarchical Localization at Large Scalecited by 559
  6. 2017Fine-tuning CNN Image Retrieval with No Human Annotationcited by 499
  7. 2021Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognitioncited by 238
  8. 2018Neighbourhood Consensus Networkscited by 174
  9. 2015Particular object retrieval with integral max-pooling of CNN activationscited by 161
  10. 2019Bridging the Domain Gap for Ground-to-Aerial Image Matchingcited by 95
  11. 2017Camera Relocalization by Computing Pairwise Relative Poses Using Convolutional Neural Networkcited by 79
  12. 2018Cross-View Image Synthesis using Conditional GANscited by 69
9 more
  1. 2019To Learn or Not to Learn: Visual Localization from Essential Matricescited by 61
  2. 2020Learning and aggregating deep local descriptors for instance-level recognitioncited by 55
  3. 2022Learning Super-Features for Image Retrievalcited by 35
  4. 2020Bayesian Triplet Loss: Uncertainty Quantification in Image Retrievalcited by 32
  5. 2018Cross-view image synthesis using geometry-guided conditional GANscited by 30
  6. 2019Condition-Invariant Multi-View Place Recognitioncited by 18
  7. 2020UR2KiD: Unifying Retrieval, Keypoint Detection, and Keypoint Description without Local Correspondence Supervisioncited by 17
  8. 2015PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalizationcited by 11
  9. 2019SuperNCN: Neighbourhood consensus network for robust outdoor scenes matchingcited by 1

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 2; 2024: 6; 2025: 1.

12 papers.

  1. 2025AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesiscited by 39
  2. 2023Visual Place Recognition: A Tutorialcited by 31
  3. 2023Multiview Aerial Visual Recognition (MAVREC): Can Multi-view Improve Aerial Visual Perception?cited by 18
  4. 2024Video2BEV: Transforming Drone Videos to BEVs for Video-based Geo-localizationcited by 17
  5. 2022VPAIR -- Aerial Visual Place Recognition and Localization in Large-scale Outdoor Environmentscited by 15
  6. 2024GOMAA-Geo: GOal Modality Agnostic Active Geo-localizationcited by 11
  7. 2024MeshVPR: Citywide Visual Place Recognition Using 3D Meshescited by 8
  8. 2022Aerial View Localization with Reinforcement Learning: Towards Emulating Search-and-Rescuecited by 4
  9. 2024Visual place recognition for aerial imagery: A surveycited by 4
  10. 2024Toon3D: Seeing Cartoons from New Perspectivescited by 3
  11. 2022ReF -- Rotation Equivariant Features for Local Feature Matchingcited by 2
  12. 2024Addressing the challenges of loop detection in agricultural environmentscited by 1