SkyLink: A Large Vision-Language Model Driven Re-ranking Framework for Cross-View UAV 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_ | 1866910223109718016 |
|---|---|
| author | Liu, Bowen Jia, Pengyue Wang, Wanyu Xu, Derong Cheng, Jiawei Dong, Jiancheng Han, Xiao Zhao, Zimo Zhang, Chao Yu, Bowen Hong, Fangyu Zhao, Xiangyu |
| author_facet | Liu, Bowen Jia, Pengyue Wang, Wanyu Xu, Derong Cheng, Jiawei Dong, Jiancheng Han, Xiao Zhao, Zimo Zhang, Chao Yu, Bowen Hong, Fangyu Zhao, Xiangyu |
| contents | Cross-view UAV geolocalization is fundamentally a challenging large-scale image retrieval task, aiming to determine the geographic coordinates of Unmanned Aerial Vehicle (UAV) queries by matching them against an extensive geo-tagged satellite image database. Most existing methods learn separate feature representations for each view and determine the final prediction using naive heuristics to assess feature similarity, thereby neglecting to model the crucial cross-view relationships. In this paper, we propose SkyLink, a novel plug-and-play ranking framework that pioneers joint relational modeling of inter-view relationships to enhance cross-view UAV geolocalization. SkyLink leverages a Large Vision-Language Model (LVLM) to model the intricate visual-semantic relationships between UAV and satellite views, facilitating effective cross-view matching. To further refine the learning process, we introduce a relational-aware loss. It leverages soft labels to provide a more nuanced supervision signal, mitigating the harsh penalty on near-positive pairs. This approach enhances both training stability and the model's discriminative capacity. Extensive experiments conducted across multiple base retrieval architectures and benchmark datasets demonstrate that SkyLink significantly boosts the ranking effectiveness of existing models, consistently achieving superior performance in various challenging scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_08063 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SkyLink: A Large Vision-Language Model Driven Re-ranking Framework for Cross-View UAV geolocalization Liu, Bowen Jia, Pengyue Wang, Wanyu Xu, Derong Cheng, Jiawei Dong, Jiancheng Han, Xiao Zhao, Zimo Zhang, Chao Yu, Bowen Hong, Fangyu Zhao, Xiangyu Computer Vision and Pattern Recognition Cross-view UAV geolocalization is fundamentally a challenging large-scale image retrieval task, aiming to determine the geographic coordinates of Unmanned Aerial Vehicle (UAV) queries by matching them against an extensive geo-tagged satellite image database. Most existing methods learn separate feature representations for each view and determine the final prediction using naive heuristics to assess feature similarity, thereby neglecting to model the crucial cross-view relationships. In this paper, we propose SkyLink, a novel plug-and-play ranking framework that pioneers joint relational modeling of inter-view relationships to enhance cross-view UAV geolocalization. SkyLink leverages a Large Vision-Language Model (LVLM) to model the intricate visual-semantic relationships between UAV and satellite views, facilitating effective cross-view matching. To further refine the learning process, we introduce a relational-aware loss. It leverages soft labels to provide a more nuanced supervision signal, mitigating the harsh penalty on near-positive pairs. This approach enhances both training stability and the model's discriminative capacity. Extensive experiments conducted across multiple base retrieval architectures and benchmark datasets demonstrate that SkyLink significantly boosts the ranking effectiveness of existing models, consistently achieving superior performance in various challenging scenarios. |
| title | SkyLink: A Large Vision-Language Model Driven Re-ranking Framework for Cross-View UAV geolocalization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.08063 |