GeoRouter: Dynamic Paradigm Routing for Worldwide Image Geolocalization
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917361654693888 |
|---|---|
| author | Jia, Pengyue Xu, Derong Zhang, Yingyi Li, Xiaopeng Zhang, Wenlin Wen, Yi Zhu, Yuanshao Zhao, Xiangyu |
| author_facet | Jia, Pengyue Xu, Derong Zhang, Yingyi Li, Xiaopeng Zhang, Wenlin Wen, Yi Zhu, Yuanshao Zhao, Xiangyu |
| contents | Worldwide image geolocalization aims to predict precise GPS coordinates for images captured anywhere on Earth, which is challenging due to the large visual and geographic diversity. Recent methods mainly follow two paradigms: retrieval-based approaches that match queries against a reference database, and generation-based approaches that directly predict coordinates using Large Vision-Language Models (LVLMs). However, we observe distinct error profiles between them: retrieval excels at fine-grained instance matching, while generation offers robust semantic reasoning. This complementary heterogeneity suggests that no single paradigm is universally superior. To harness this potential, we propose GeoRouter, a dynamic routing framework that adaptively assigns each query to the optimal paradigm. GeoRouter leverages an LVLM backbone to analyze visual content and provide routing decisions. To optimize GeoRouter, we introduce a distance-aware preference objective that converts the distance gap between paradigms into a continuous supervision signal, explicitly reflecting relative performance differences. Furthermore, we construct GeoRouting, the first large-scale dataset tailored for training routing policies with independent paradigm predictions. Extensive experiments on IM2GPS3k and YFCC4k demonstrate that GeoRouter significantly outperforms state-of-the-art baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_24376 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GeoRouter: Dynamic Paradigm Routing for Worldwide Image Geolocalization Jia, Pengyue Xu, Derong Zhang, Yingyi Li, Xiaopeng Zhang, Wenlin Wen, Yi Zhu, Yuanshao Zhao, Xiangyu Computer Vision and Pattern Recognition Worldwide image geolocalization aims to predict precise GPS coordinates for images captured anywhere on Earth, which is challenging due to the large visual and geographic diversity. Recent methods mainly follow two paradigms: retrieval-based approaches that match queries against a reference database, and generation-based approaches that directly predict coordinates using Large Vision-Language Models (LVLMs). However, we observe distinct error profiles between them: retrieval excels at fine-grained instance matching, while generation offers robust semantic reasoning. This complementary heterogeneity suggests that no single paradigm is universally superior. To harness this potential, we propose GeoRouter, a dynamic routing framework that adaptively assigns each query to the optimal paradigm. GeoRouter leverages an LVLM backbone to analyze visual content and provide routing decisions. To optimize GeoRouter, we introduce a distance-aware preference objective that converts the distance gap between paradigms into a continuous supervision signal, explicitly reflecting relative performance differences. Furthermore, we construct GeoRouting, the first large-scale dataset tailored for training routing policies with independent paradigm predictions. Extensive experiments on IM2GPS3k and YFCC4k demonstrate that GeoRouter significantly outperforms state-of-the-art baselines. |
| title | GeoRouter: Dynamic Paradigm Routing for Worldwide Image Geolocalization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.24376 |