This is a model of the approach described in the paper "Around the World in 80 Timesteps: A Generative Approach to Global Visual Geolocation"

@misc{dufour2024world80timestepsgenerative,
      title={Around the World in 80 Timesteps: A Generative Approach to Global Visual Geolocation}, 
      author={Nicolas Dufour and David Picard and Vicky Kalogeiton and Loic Landrieu},
      year={2024},
      eprint={2412.06781},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2412.06781}, 
}
pip install diff-plonk
from plonk import PLONKPipeline

pipeline = PLONKPipeline.from_pretrained("nicolas-dufour/PLONK_YFCC")

gps_coords = pipeline(images, batch_size=1024)
Downloads last month
170
Safetensors
Model size
36M params
Tensor type
F32
ยท
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.

Space using nicolas-dufour/PLONK_YFCC 1

Collection including nicolas-dufour/PLONK_YFCC