A generative model using diffusion and Riemannian flow matching on the sphere achieves state-of-the-art visual geolocation and outputs full probability maps over possible locations.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Around the World in 80 Timesteps: A Generative Approach to Global Visual Geolocation
A generative model using diffusion and Riemannian flow matching on the sphere achieves state-of-the-art visual geolocation and outputs full probability maps over possible locations.