TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Datasets/CV-Cities

CV-Cities

Imagesbsd-3-clauseIntroduced 2024-11-19

CV-Cities comprises 223,736223,736223,736 ground panoramic images and an equal number of satellite images all accompanied by high-precision GPS coordinates. These images represent sixteen representative cities across five continents. The ground images are 360∘360^{\circ}360∘ panorama images with a resolution of 4,096×2,0484,096 \times 2,0484,096×2,048 pixels, while the resolution of satellite images is 746×746746 \times 746746×746 pixels, and are captured at a zoom level of 202020. The spatial resolution is 0.298m0.298 m0.298m, corresponding to a latitude and longitude range of 0.002×0.002∘0.002 \times 0.002^{\circ}0.002×0.002∘ (about 222×222m222 \times 222 m222×222m). The images of each city in the dataset can be used for training and testing purposes.

Benchmarks

Visual Place Recognition/Recall@1Visual Place Recognition/Recall@5

Statistics

Papers
3
Benchmarks
2

Links

Homepage

Tasks

Image RetrievalVisual Place Recognitiongeo-localization