Metraipolis › archive › dc_194d453fc45a
What Words Keep of a Place: Zero-Shot Language Reasoning for Cross-View Geo-Localization — arXiv:2610.07269
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.07269
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T11:42:19.168Z
- SHA-256 of the archived text
ec0606eb7dd7a11a1da1737b3e4967782eb33f96f56bdeaa741fc5aeed008b6d- Stable URL of this page
https://metraipolis.com/documento/dc_194d453fc45a
How to cite
What Words Keep of a Place: Zero-Shot Language Reasoning for Cross-View Geo-Localization — arXiv:2610.07269 — arXiv (en), https://arxiv.org/abs/2610.07269 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_194d453fc45a (Metraipolis archive dc_194d453fc45a, sha256 ec0606eb7dd7a11a1da1737b3e4967782eb33f96f56bdeaa741fc5aeed008b6d)
BibTeX
@misc{dc194d453fc45a,
title = {What Words Keep of a Place: Zero-Shot Language Reasoning for Cross-View Geo-Localization — arXiv:2610.07269},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.07269},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_194d453fc45a; sha256 ec0606eb7dd7a11a1da1737b3e4967782eb33f96f56bdeaa741fc5aeed008b6d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07269. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Cross-view geo-localization is commonly solved as an image retrieval problem, matching a ground-level image against a database of satellite tiles through a jointly trained embedding. Such models are accurate, but they need large paired supervision and cannot show what evidence supports a match. In this paper, we study a different question: how much of this task can be solved through language alone? We prompt a multimodal large language model (MLLM) to describe each ground panorama and each satellite tile as structured text, and localize by comparing these descriptions. No component is trained. We evaluate on 9,826 VIGOR pairs from four U.S. cities, in three settings. First, the descriptions are faithful but not discriminative. They agree closely across the two views, yet ranking the full pool by description similarity almost never returns the correct tile (0.39% Recall@1). Second, we narrow the pool to ten neighboring tiles, as a coarse prior would do. The same descriptions now become useful: an MLLM judge that scores structural consistency doubles random ranking and matches a strong lexical baseline. It also states which fields of the two descriptions agree and which conflict, which an embedding distance cannot do, and which we see as a step toward interpretable localization. Third, we place the judge on a trained visual retriever. On the queries it ranks wrongly, reranking from images works, while reranking from our descriptions does not (23.5% against 10.7% Recall@1). Scene structure survives the conversion into language, while the fine appearance detail needed to separate nearby places does not. Code and prompts are publicly available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.07269 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T11:19:24.884Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).