Viewpoint Invariant Dense Matching For Visual Geolocalization

Abstract

In this paper we propose a novel method for image matching based on dense local features and tailored for visual geolocalization. Dense local features matching is robust against changes in illumination and occlusions, but not against viewpoint shifts which are a fundamental aspect of geolocalization. Our method, called GeoWarp, directly embeds invariance to viewpoint shifts in the process of extracting dense features. This is achieved via a trainable module which learns from the data an invariance that is meaningful for the task of recognizing places. We also devise a new self-supervised loss and two new weakly supervised losses to train this module using only unlabeled data and weak labels. GeoWarp is implemented efficiently as a re-ranking method that can be easily embedded into pre-existing visual geolocalization pipelines. Experimental validation on standard geolocalization benchmarks demonstrates that GeoWarp boosts the accuracy of state-of-the-art retrieval architectures. The cod

Stats

• citations32
• S2 citations—
• github stars66
• HF likes0
• heat score15.04
• arxiv keyberton2021viewpoint

Related papers

• Just Zoom In: Cross-view Geo-localization Via Autoregressive Zooming (2026)0.00
• Sparse-to-dense Hypercolumn Matching For Long-term Visual Localization (2019)12.99
• BEV-CV: Birds-eye-view Transform For Cross-view Geo-localisation (2023)5.84
• VIGOR: Cross-view Image Geo-localization Beyond One-to-one Retrieval (2020)21.49
• Cross-view Image Matching For Geo-localization In Urban Environments (2017)17.16
• VICI: Vlm-instructed Cross-view Image-localisation (2025)2.51
• Clnet: Cross-view Correspondence Makes A Stronger Geo-localizationer (2025)0.00
• Geo-localization Via Ground-to-satellite Cross-view Image Retrieval (2022)12.54