Cross-view geolocalization (CVGL) systems, while effective at retrieving a list of relevant candidates (high Recall@k), often fail to identify the single best match (low Top-1 accuracy). This work investigates the use of zero-shot Vision-Language Models (VLMs) as rerankers to address this gap. We propose a two-stage framework: state-of-the-art (SOTA) retrieval followed by VLM reranking. We systematically compare two strategies: (1) Pointwise (scoring candidates individually) and (2) Pairwise (comparing candidates relatively). Experiments on the VIGOR dataset show a clear divergence: all pointwise methods cause a catastrophic drop in performance or no change at all. In contrast, a pairwise comparison strategy using LLaVA improves Top-1 accuracy over the strong retrieval baseline. Our analysis concludes that, these VLMs are poorly calibrated for absolute relevance scoring but are effective at fine-grained relative visual judgment, making pairwise reranking a promising direction for enhancing CVGL precision.
@article{arxiv.2603.27251,
title = {Zero-shot Vision-Language Reranking for Cross-View Geolocalization},
author = {Yunus Talha Erzurumlu and John E. Anderson and William J. Shuart and Charles Toth and Alper Yilmaz},
journal= {arXiv preprint arXiv:2603.27251},
year = {2026}
}
Comments
7 pages, 4 figures. Accepted to XXV ISPRS Congress