Search papers, labs, and topics across Lattice.
This paper introduces GeoLink, a 3D-aware framework for cross-view geo-localization that enhances generalization by leveraging 3D structural priors derived from point clouds reconstructed from drone imagery. GeoLink uses a Geometric-aware Semantic Refinement module to reduce view-biased dependencies in 2D features and a Unified View Relation Distillation module to transfer 3D structural relationships to 2D features. Experiments demonstrate that GeoLink achieves state-of-the-art performance and superior generalization across unseen domains and diverse weather conditions.
By injecting 3D structural awareness into 2D representations, GeoLink achieves remarkable gains in cross-view geo-localization generalization, even in challenging unseen domains and weather conditions.
Generalizable cross-view geo-localization aims to match the same location across views in unseen regions and conditions without GPS supervision. Its core difficulty lies in severe semantic inconsistency caused by viewpoint variation and poor generalization under domain shift. Existing methods mainly rely on 2D correspondence, but they are easily distracted by redundant shared information across views, leading to less transferable representations. To address this, we propose GeoLink, a 3D-aware semantic-consistent framework for Generalizable cross-view geo-localization. Specifically, we offline reconstruct scene point clouds from multi-view drone images using VGGT, providing stable structural priors. Based on these 3D anchors, we improve 2D representation learning in two complementary ways. A Geometric-aware Semantic Refinement module mitigates potentially redundant and view-biased dependencies in 2D features under 3D guidance. In addition, a Unified View Relation Distillation module transfers 3D structural relations to 2D features, improving cross-view alignment while preserving a 2D-only inference pipeline. Extensive experiments on multiple benchmarks show that GeoLink consistently outperforms state-of-the-art methods and achieves superior generalization across unseen domains and diverse weather environments.
