README.md

---
title: Plonk
emoji: 👀
colorFrom: yellow
colorTo: purple
sdk: gradio
sdk_version: 4.27.0
app_file: app.py
pinned: false
license: mit
---

![image/png](https://cdn-uploads.huggingface.co/production/uploads/654bb2591a9e65ef2598d8c4/kI6m3p8P9SD2VoQ6E5WB5.png)

# OpenStreetView-5M <br><sub>The Many Roads to Global Visual Geolocation 📍🌍</sub>

Demo for [OpenStreetView-5M: The Many Roads to Global Visual Geolocation](https://imagine.enpc.fr/~ioannis.siglidis/osv5m/).  
[OpenStreetView-5M](https://huggingface.co/datasets/osv5m/osv5m) is the first large-scale open geolocation benchmark of streetview images.  

**First authors:** [Guillaume Astruc](https://gastruc.github.io/), [Nicolas Dufour](https://nicolas-dufour.github.io/), [Ioannis Siglidis](https://imagine.enpc.fr/~siglidii/)  
**Second authors:** [Constantin Aronssohn](), Nacim Bouia, [Stephanie Fu](https://stephanie-fu.github.io/), [Romain Loiseau](https://romainloiseau.fr/), [Van Nguyen Nguyen](https://nv-nguyen.github.io/), [Charles Raude](https://imagine.enpc.fr/~raudec/), [Elliot Vincent](https://imagine.enpc.fr/~vincente/), Lintao XU, Hongyu Zhou  
**Last author:** [Loic Landrieu](https://loiclandrieu.com/)  
**Research Institute:** [Imagine](https://imagine.enpc.fr/), _LIGM, Ecole des Ponts, Univ Gustave Eiffel, CNRS, Marne-la-Vallée, France_  

For more details and results, please check out our [paper](https://arxiv.org/abs/2404.18873) and [project page](https://imagine.enpc.fr/~ioannis.siglidis/osv5m/).  

### Citing 💫

```bibtex
@article{osv5m,
    title = {{OpenStreetView-5M}: {T}he Many Roads to Global Visual Geolocation},
    author = {Astruc, Guillaume and Dufour, Nicolas and Siglidis, Ioannis
      and Aronssohn, Constantin and Bouia, Nacim and Fu, Stephanie and Loiseau, Romain
      and Nguyen, Van Nguyen and Raude, Charles and Vincent, Elliot and Xu, Lintao
      and Zhou, Hongyu and Landrieu, Loic},
    journal = {CVPR},
    year = {2024},
  }
```

### Acknowledgements
OSV-5M was made possible through the generous support of the Mapillary team, which helped us navigate their vast street view image database. Our work was supported by the ANR project READY3D ANR-19-CE23-0007, and the HPC resources of IDRIS under the allocation AD011014719 made by GENCI.
We thank Valérie Gouet for her valuable feedback; Ségolène Albouy for helping us make gradio-folium clickable.