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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dufour, Nicolas, Picard, David, Kalogeiton, Vicky, Landrieu, Loic
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910735189147648
author Dufour, Nicolas
Picard, David
Kalogeiton, Vicky
Landrieu, Loic
author_facet Dufour, Nicolas
Picard, David
Kalogeiton, Vicky
Landrieu, Loic
contents Global visual geolocation predicts where an image was captured on Earth. Since images vary in how precisely they can be localized, this task inherently involves a significant degree of ambiguity. However, existing approaches are deterministic and overlook this aspect. In this paper, we aim to close the gap between traditional geolocalization and modern generative methods. We propose the first generative geolocation approach based on diffusion and Riemannian flow matching, where the denoising process operates directly on the Earth's surface. Our model achieves state-of-the-art performance on three visual geolocation benchmarks: OpenStreetView-5M, YFCC-100M, and iNat21. In addition, we introduce the task of probabilistic visual geolocation, where the model predicts a probability distribution over all possible locations instead of a single point. We introduce new metrics and baselines for this task, demonstrating the advantages of our diffusion-based approach. Codes and models will be made available.
format Preprint
id arxiv_https___arxiv_org_abs_2412_06781
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Around the World in 80 Timesteps: A Generative Approach to Global Visual Geolocation
Dufour, Nicolas
Picard, David
Kalogeiton, Vicky
Landrieu, Loic
Computer Vision and Pattern Recognition
Machine Learning
Global visual geolocation predicts where an image was captured on Earth. Since images vary in how precisely they can be localized, this task inherently involves a significant degree of ambiguity. However, existing approaches are deterministic and overlook this aspect. In this paper, we aim to close the gap between traditional geolocalization and modern generative methods. We propose the first generative geolocation approach based on diffusion and Riemannian flow matching, where the denoising process operates directly on the Earth's surface. Our model achieves state-of-the-art performance on three visual geolocation benchmarks: OpenStreetView-5M, YFCC-100M, and iNat21. In addition, we introduce the task of probabilistic visual geolocation, where the model predicts a probability distribution over all possible locations instead of a single point. We introduce new metrics and baselines for this task, demonstrating the advantages of our diffusion-based approach. Codes and models will be made available.
title Around the World in 80 Timesteps: A Generative Approach to Global Visual Geolocation
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2412.06781