GeoSURGE: Geo-localization using Semantic Fusion with Hierarchy of Geographic Embeddings
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910077295788032 |
|---|---|
| author | Daruna, Angel Meegan, Nicholas Chiu, Han-Pang Samarasekera, Supun Kumar, Rakesh |
| author_facet | Daruna, Angel Meegan, Nicholas Chiu, Han-Pang Samarasekera, Supun Kumar, Rakesh |
| contents | Worldwide visual geo-localization aims to determine the geographic location of an image anywhere on Earth using only its visual content. Despite recent progress, learning expressive representations of geographic space remains challenging due to the inherently low-dimensional nature of geographic coordinates. We formulate global geo-localization as aligning the visual representation of a query image with a learned geographic representation. Our approach explicitly models the world as a hierarchy of learned geographic embeddings, enabling a distributed and multi-scale representation of geographic space. In addition, we introduce a semantic fusion module that efficiently integrates appearance features with semantic segmentation through latent cross-attention, producing a more robust visual representation for localization. Experiments on five widely used geo-localization benchmarks demonstrate that our method achieves new state-of-the-art results on 22 of 25 reported metrics. Ablation studies show that these improvements are primarily driven by the proposed geographic representation and semantic fusion mechanism. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_01448 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GeoSURGE: Geo-localization using Semantic Fusion with Hierarchy of Geographic Embeddings Daruna, Angel Meegan, Nicholas Chiu, Han-Pang Samarasekera, Supun Kumar, Rakesh Computer Vision and Pattern Recognition Artificial Intelligence Worldwide visual geo-localization aims to determine the geographic location of an image anywhere on Earth using only its visual content. Despite recent progress, learning expressive representations of geographic space remains challenging due to the inherently low-dimensional nature of geographic coordinates. We formulate global geo-localization as aligning the visual representation of a query image with a learned geographic representation. Our approach explicitly models the world as a hierarchy of learned geographic embeddings, enabling a distributed and multi-scale representation of geographic space. In addition, we introduce a semantic fusion module that efficiently integrates appearance features with semantic segmentation through latent cross-attention, producing a more robust visual representation for localization. Experiments on five widely used geo-localization benchmarks demonstrate that our method achieves new state-of-the-art results on 22 of 25 reported metrics. Ablation studies show that these improvements are primarily driven by the proposed geographic representation and semantic fusion mechanism. |
| title | GeoSURGE: Geo-localization using Semantic Fusion with Hierarchy of Geographic Embeddings |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2510.01448 |