Saved in:
Bibliographic Details
Main Authors: Lu, Jun, Sang, Zehao, Wei, Haoqi, Liu, Xiangyun, Zhu, Kun, Guo, Haitao, Gong, Zhihui, Ding, Lei
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.13855
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917341685612544
author Lu, Jun
Sang, Zehao
Wei, Haoqi
Liu, Xiangyun
Zhu, Kun
Guo, Haitao
Gong, Zhihui
Ding, Lei
author_facet Lu, Jun
Sang, Zehao
Wei, Haoqi
Liu, Xiangyun
Zhu, Kun
Guo, Haitao
Gong, Zhihui
Ding, Lei
contents Cross-View Geo-Localization (CVGL) in remote sensing aims to locate a drone-view query by matching it to geo-tagged satellite images. Although supervised methods have achieved strong results on closeset benchmarks, they often fail to generalize to unconstrained, real-world scenarios due to severe viewpoint differences and dataset bias. To overcome these limitations, we present VFM-Loc, a training-free framework for zero-shot CVGL that leverages the generalizable visual representations from vision foundational models (VFMs). VFM-Loc identifies and matches discriminative visual clues across different viewpoints through a progressive alignment strategy. First, we design a hierarchical clue extraction mechanism using Generalized Mean pooling and Scale-Weighted RMAC to preserve distinctive visual clues across scales while maintaining hierarchical confidence. Second, we introduce a statistical manifold alignment pipeline based on domain-wise PCA and Orthogonal Procrustes analysis, linearly aligning heterogeneous feature distributions in a shared metric space. Experiments demonstrate that VFM-Loc exhibits strong zero-shot accuracy on standard benchmarks and surpasses supervised methods by over 20% in Recall@1 on the challenging LO-UCV dataset with large oblique angles. This work highlights that principled alignment of pre-trained features can effectively bridge the cross-view gap, establishing a robust and training-free paradigm for real-world CVGL. The relevant code is made available at: https://github.com/DingLei14/VFM-Loc.
format Preprint
id arxiv_https___arxiv_org_abs_2603_13855
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle VFM-Loc: Zero-Shot Cross-View Geo-Localization via Aligning Discriminative Visual Hierarchies
Lu, Jun
Sang, Zehao
Wei, Haoqi
Liu, Xiangyun
Zhu, Kun
Guo, Haitao
Gong, Zhihui
Ding, Lei
Computer Vision and Pattern Recognition
Cross-View Geo-Localization (CVGL) in remote sensing aims to locate a drone-view query by matching it to geo-tagged satellite images. Although supervised methods have achieved strong results on closeset benchmarks, they often fail to generalize to unconstrained, real-world scenarios due to severe viewpoint differences and dataset bias. To overcome these limitations, we present VFM-Loc, a training-free framework for zero-shot CVGL that leverages the generalizable visual representations from vision foundational models (VFMs). VFM-Loc identifies and matches discriminative visual clues across different viewpoints through a progressive alignment strategy. First, we design a hierarchical clue extraction mechanism using Generalized Mean pooling and Scale-Weighted RMAC to preserve distinctive visual clues across scales while maintaining hierarchical confidence. Second, we introduce a statistical manifold alignment pipeline based on domain-wise PCA and Orthogonal Procrustes analysis, linearly aligning heterogeneous feature distributions in a shared metric space. Experiments demonstrate that VFM-Loc exhibits strong zero-shot accuracy on standard benchmarks and surpasses supervised methods by over 20% in Recall@1 on the challenging LO-UCV dataset with large oblique angles. This work highlights that principled alignment of pre-trained features can effectively bridge the cross-view gap, establishing a robust and training-free paradigm for real-world CVGL. The relevant code is made available at: https://github.com/DingLei14/VFM-Loc.
title VFM-Loc: Zero-Shot Cross-View Geo-Localization via Aligning Discriminative Visual Hierarchies
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.13855