SkyLink: Unifying Street-Satellite Geo-Localization via UAV-Mediated 3D Scene Alignment
This work improves geo-localization for urban mapping and navigation by integrating UAV-mediated 3D scene alignment, though it is incremental with hybrid methods.
The paper tackles the problem of cross-view geo-localization between street and satellite images by addressing semantic degradation from extreme viewpoint disparities, achieving 25.75% Recall@1 accuracy on the University-1652 dataset in the UAVM2025 Challenge.
Cross-view geo-localization aims at establishing location correspondences between different viewpoints. Existing approaches typically learn cross-view correlations through direct feature similarity matching, often overlooking semantic degradation caused by extreme viewpoint disparities. To address this unique problem, we focus on robust feature retrieval under viewpoint variation and propose the novel SkyLink method. We firstly utilize the Google Retrieval Enhancement Module to perform data enhancement on street images, which mitigates the occlusion of the key target due to restricted street viewpoints. The Patch-Aware Feature Aggregation module is further adopted to emphasize multiple local feature aggregations to ensure the consistent feature extraction across viewpoints. Meanwhile, we integrate the 3D scene information constructed from multi-scale UAV images as a bridge between street and satellite viewpoints, and perform feature alignment through self-supervised and cross-view contrastive learning. Experimental results demonstrate robustness and generalization across diverse urban scenarios, which achieve 25.75$\%$ Recall@1 accuracy on University-1652 in the UAVM2025 Challenge. Code will be released at https://github.com/HRT00/CVGL-3D.