GeoRanker: Distance-Aware Ranking for Worldwide Image Geolocalization

TL;DR

GeoRanker is a novel distance-aware ranking framework utilizing vision-language models and multi-order distance loss to improve worldwide image geolocalization accuracy, outperforming existing methods on key benchmarks.

Contribution

Introduces GeoRanker, a distance-aware ranking model with a multi-order distance loss and a new dataset for geographic ranking, advancing state-of-the-art in image geolocalization.

Findings

Achieves state-of-the-art results on IM2GPS3K and YFCC4K benchmarks.

Significantly outperforms previous methods in geolocalization accuracy.

Demonstrates effectiveness of distance-aware ranking with multimodal encoding.

Abstract

Worldwide image geolocalization-the task of predicting GPS coordinates from images taken anywhere on Earth-poses a fundamental challenge due to the vast diversity in visual content across regions. While recent approaches adopt a two-stage pipeline of retrieving candidates and selecting the best match, they typically rely on simplistic similarity heuristics and point-wise supervision, failing to model spatial relationships among candidates. In this paper, we propose GeoRanker, a distance-aware ranking framework that leverages large vision-language models to jointly encode query-candidate interactions and predict geographic proximity. In addition, we introduce a multi-order distance loss that ranks both absolute and relative distances, enabling the model to reason over structured spatial relationships. To support this, we curate GeoRanking, the first dataset explicitly designed for geographic ranking tasks with multimodal candidate information. GeoRanker achieves state-of-the-art results on two well-established benchmarks (IM2GPS3K and YFCC4K), significantly outperforming current best methods.