Search papers, labs, and topics across Lattice.
This paper introduces a geometry-aware framework for UAV cross-view geo-localization that unifies place recognition and pose estimation by explicitly modeling 3D scene geometry. They reconstruct a local 3D scene from UAV images using a Visual Geometry Grounded Transformer (VGGT) and render a virtual Bird's-Eye View (BEV) to align with satellite imagery. A Satellite-wise Attention Block efficiently handles multiple location hypotheses, achieving state-of-the-art meter-level localization accuracy on the University-1652 and SUES-200 datasets.
By explicitly modeling 3D scene geometry, this UAV geo-localization method achieves meter-level accuracy, outperforming existing approaches that treat perspective distortion as mere noise.
Cross-view geo-localization for Unmanned Aerial Vehicles (UAVs) operating in GNSS-denied environments remains challenging due to the severe geometric discrepancy between oblique UAV imagery and orthogonal satellite maps. Most existing methods address this problem through a decoupled pipeline of place retrieval and pose estimation, implicitly treating perspective distortion as appearance noise rather than an explicit geometric transformation. In this work, we propose a geometry-aware UAV geo-localization framework that explicitly models the 3D scene geometry to unify coarse place recognition and fine-grained pose estimation within a single inference pipeline. Our approach reconstructs a local 3D scene from multi-view UAV image sequences using a Visual Geometry Grounded Transformer (VGGT), and renders a virtual Bird's-Eye View (BEV) representation that orthorectifies the UAV perspective to align with satellite imagery. This BEV serves as a geometric intermediary that enables robust cross-view retrieval and provides spatial priors for accurate 3 Degrees of Freedom (3-DoF) pose regression. To efficiently handle multiple location hypotheses, we introduce a Satellite-wise Attention Block that isolates the interaction between each satellite candidate and the reconstructed UAV scene, preventing inter-candidate interference while maintaining linear computational complexity. In addition, we release a recalibrated version of the University-1652 dataset with precise coordinate annotations and spatial overlap analysis, enabling rigorous evaluation of end-to-end localization accuracy. Extensive experiments on the refined University-1652 benchmark and SUES-200 demonstrate that our method significantly outperforms state-of-the-art baselines, achieving robust meter-level localization accuracy and improved generalization in complex urban environments.
