GeoBridge: A Semantic-Anchored Multi-View Foundation Model Bridging Images and Text for Geo-Localization
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914474879877120 |
|---|---|
| author | Song, Zixuan Zhang, Jing Wang, Di Zhou, Zidie Liu, Wenbin Guo, Haonan Wang, En Du, Bo |
| author_facet | Song, Zixuan Zhang, Jing Wang, Di Zhou, Zidie Liu, Wenbin Guo, Haonan Wang, En Du, Bo |
| contents | Cross-view geo-localization infers a location by retrieving geo-tagged reference images that visually correspond to a query image. However, the traditional satellite-centric paradigm limits robustness when high-resolution or up-to-date satellite imagery is unavailable. It further underexploits complementary cues across views (\eg, drone, satellite, and street) and modalities (\eg, language and image). To address these challenges, we propose GeoBridge, a novel model that performs bidirectional matching across views and supports language-to-image retrieval. Going beyond traditional satellite-centric formulations, GeoBridge builds on a novel semantic-anchor mechanism that bridges multi-view features through textual descriptions for robust, flexible localization. In support of this task, we construct GeoLoc, the first large-scale, cross-modal, and multi-view aligned dataset comprising over 50,000 pairs of drone, street-view panorama, and satellite images as well as their textual descriptions, collected from 36 countries, ensuring both geographic and semantic alignment. We performed broad evaluations across multiple tasks. Experiments confirm that GeoLoc pre-training markedly improves geo-location accuracy for GeoBridge while promoting cross-domain generalization and cross-modal knowledge transfer. Code, dataset, and pretrained models will be released at https://github.com/MiliLab/GeoBridge. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_02697 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GeoBridge: A Semantic-Anchored Multi-View Foundation Model Bridging Images and Text for Geo-Localization Song, Zixuan Zhang, Jing Wang, Di Zhou, Zidie Liu, Wenbin Guo, Haonan Wang, En Du, Bo Computer Vision and Pattern Recognition Cross-view geo-localization infers a location by retrieving geo-tagged reference images that visually correspond to a query image. However, the traditional satellite-centric paradigm limits robustness when high-resolution or up-to-date satellite imagery is unavailable. It further underexploits complementary cues across views (\eg, drone, satellite, and street) and modalities (\eg, language and image). To address these challenges, we propose GeoBridge, a novel model that performs bidirectional matching across views and supports language-to-image retrieval. Going beyond traditional satellite-centric formulations, GeoBridge builds on a novel semantic-anchor mechanism that bridges multi-view features through textual descriptions for robust, flexible localization. In support of this task, we construct GeoLoc, the first large-scale, cross-modal, and multi-view aligned dataset comprising over 50,000 pairs of drone, street-view panorama, and satellite images as well as their textual descriptions, collected from 36 countries, ensuring both geographic and semantic alignment. We performed broad evaluations across multiple tasks. Experiments confirm that GeoLoc pre-training markedly improves geo-location accuracy for GeoBridge while promoting cross-domain generalization and cross-modal knowledge transfer. Code, dataset, and pretrained models will be released at https://github.com/MiliLab/GeoBridge. |
| title | GeoBridge: A Semantic-Anchored Multi-View Foundation Model Bridging Images and Text for Geo-Localization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.02697 |