Around the World in 80 Timesteps: A Generative Approach to Global Visual Geolocation

Figure 1. Geolocation as a Generative Process. We explore diffusion and flow matching for visual geolocation by sampling and denoising random locations. This process generates trajectories onto the Earth's surface, whose endpoints provide location estimates. Our models also provide probability densities for every possible image locations. We illustrate these trajectories and the log-densities for three images from different datasets: an Andean condor from iNat21 [74], an African open-air market from YFCC-100M [1], and a dashcam snapshot from OSV-5M [2]. The predicted image locations are indicated by and the true ones by .