DualGeo: A Dual-View Framework for Worldwide Image Geo-localization
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917443442573312 |
|---|---|
| author | Cui, Junchao Shi, Wenqi Du, Shaoyong He, Hang Ma, Xuanzi Tang, Hao Luo, Xiangyang |
| author_facet | Cui, Junchao Shi, Wenqi Du, Shaoyong He, Hang Ma, Xuanzi Tang, Hao Luo, Xiangyang |
| contents | Worldwide image geo-localization aims to infer the geographic location of an image captured anywhere on Earth, spanning street, city, regional, national, and continental scales. Existing methods rely on visual features that are sensitive to environmental variations (e.g., lighting, season, and weather) and lack effective post-processing to filter outlier candidates, limiting localization accuracy. To address these limitations, we propose DualGeo, a two-stage framework for worldwide image geo-localization. First, it establishes a geo-representational foundation by fusing image and semantic segmentation features via bidirectional cross-attention. The fused features are then aligned with GPS coordinates through dual-view contrastive learning to build a global retrieval database. Second, it performs geo-cognitive refinement by re-ranking retrieved candidates using geographic clustering. It then feeds them into large multimodal models (LMMs) for final coordinate prediction. Experiments on IM2GPS, IM2GPS3k, and YFCC4k show that DualGeo outperforms state-of-the-art methods, improving street-level (<1 km) and city-level (<25 km) localization accuracy by 3.6%-16.58% and 1.29%-8.77%, respectively. Our code and datasets are available : https://github.com/CJ310177/DualGeo. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_25533 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DualGeo: A Dual-View Framework for Worldwide Image Geo-localization Cui, Junchao Shi, Wenqi Du, Shaoyong He, Hang Ma, Xuanzi Tang, Hao Luo, Xiangyang Computer Vision and Pattern Recognition Worldwide image geo-localization aims to infer the geographic location of an image captured anywhere on Earth, spanning street, city, regional, national, and continental scales. Existing methods rely on visual features that are sensitive to environmental variations (e.g., lighting, season, and weather) and lack effective post-processing to filter outlier candidates, limiting localization accuracy. To address these limitations, we propose DualGeo, a two-stage framework for worldwide image geo-localization. First, it establishes a geo-representational foundation by fusing image and semantic segmentation features via bidirectional cross-attention. The fused features are then aligned with GPS coordinates through dual-view contrastive learning to build a global retrieval database. Second, it performs geo-cognitive refinement by re-ranking retrieved candidates using geographic clustering. It then feeds them into large multimodal models (LMMs) for final coordinate prediction. Experiments on IM2GPS, IM2GPS3k, and YFCC4k show that DualGeo outperforms state-of-the-art methods, improving street-level (<1 km) and city-level (<25 km) localization accuracy by 3.6%-16.58% and 1.29%-8.77%, respectively. Our code and datasets are available : https://github.com/CJ310177/DualGeo. |
| title | DualGeo: A Dual-View Framework for Worldwide Image Geo-localization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.25533 |