GeoSearch: Augmenting Worldwide Geolocalization with Web-Scale Reverse Image Search and Image Matching

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Le-Duc, Tung-Duong, Nguyen-Son, Hoang-Quoc, Dao, Minh-Son
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911628143886336
author Le-Duc, Tung-Duong
Nguyen-Son, Hoang-Quoc
Dao, Minh-Son
author_facet Le-Duc, Tung-Duong
Nguyen-Son, Hoang-Quoc
Dao, Minh-Son
contents Worldwide image geolocalization, which aims to predict the GPS coordinates of any image on Earth, remains challenging due to global visual diversity. Recent generative approaches based on Retrieval-Augmented Generation (RAG) and Large Multimodal Models (LMMs) leverage candidates retrieved from fixed databases for reasoning, but often struggle with scenes that are absent from the reference set. In this work, we propose GeoSearch, an open-world geolocation framework that integrates web-scale reverse image search into the RAG pipeline. GeoSearch augments LMM prompts with database-retrieved coordinates and textual evidence extracted from web pages. To mitigate noise from irrelevant content, we introduce a two-layer filtering mechanism consisting of image matching, followed by confidence-based gating. Experiments on standard benchmarks Im2GPS3k and YFCC4k demonstrate the superiority of GeoSearch under leakage-aware evaluation. Our code and data are publicly available to support reproducibility.
format Preprint
id arxiv_https___arxiv_org_abs_2604_25390
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle GeoSearch: Augmenting Worldwide Geolocalization with Web-Scale Reverse Image Search and Image Matching
Le-Duc, Tung-Duong
Nguyen-Son, Hoang-Quoc
Dao, Minh-Son
Information Retrieval
Computer Vision and Pattern Recognition
H.3.3
Worldwide image geolocalization, which aims to predict the GPS coordinates of any image on Earth, remains challenging due to global visual diversity. Recent generative approaches based on Retrieval-Augmented Generation (RAG) and Large Multimodal Models (LMMs) leverage candidates retrieved from fixed databases for reasoning, but often struggle with scenes that are absent from the reference set. In this work, we propose GeoSearch, an open-world geolocation framework that integrates web-scale reverse image search into the RAG pipeline. GeoSearch augments LMM prompts with database-retrieved coordinates and textual evidence extracted from web pages. To mitigate noise from irrelevant content, we introduce a two-layer filtering mechanism consisting of image matching, followed by confidence-based gating. Experiments on standard benchmarks Im2GPS3k and YFCC4k demonstrate the superiority of GeoSearch under leakage-aware evaluation. Our code and data are publicly available to support reproducibility.
title GeoSearch: Augmenting Worldwide Geolocalization with Web-Scale Reverse Image Search and Image Matching
topic Information Retrieval
Computer Vision and Pattern Recognition
H.3.3
url https://arxiv.org/abs/2604.25390