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 code and trained models are available at https://github.com/gmberton/geo_warp

Viewpoint Invariant Dense Matching for Visual Geolocalization / Berton, GABRIELE MORENO; Masone, Carlo; Paolicelli, Valerio; Caputo, Barbara. - ELETTRONICO. - (2021), pp. 12149-12158. (Intervento presentato al convegno 2021 IEEE/CVF International Conference on Computer Vision (ICCV) tenutosi a Montreal (CAN) nel 10-17 October 2021) [10.1109/ICCV48922.2021.01195].

Viewpoint Invariant Dense Matching for Visual Geolocalization

Berton Gabriele;Masone Carlo;Paolicelli Valerio;Caputo Barbara
2021

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 code and trained models are available at https://github.com/gmberton/geo_warp
2021
978-1-6654-2812-5
File in questo prodotto:
File Dimensione Formato  
GeoWarp_ICCV21.pdf

accesso aperto

Descrizione: Articolo principale
Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: Pubblico - Tutti i diritti riservati
Dimensione 2 MB
Formato Adobe PDF
2 MB Adobe PDF Visualizza/Apri
Viewpoint_Invariant_Dense_Matching_for_Visual_Geolocalization.pdf

accesso riservato

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 2.5 MB
Formato Adobe PDF
2.5 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2947804