GeoSearch: Augmenting Worldwide Geolocalization with Web-Scale Reverse Image Search and Image Matching
For researchers in image geolocalization, GeoSearch addresses the limitation of fixed reference databases by leveraging dynamic web-scale search, but the improvement is incremental over existing RAG-based methods.
GeoSearch improves worldwide image geolocalization by integrating web-scale reverse image search into a RAG pipeline, achieving state-of-the-art results on Im2GPS3k and YFCC4k benchmarks under leakage-aware evaluation.
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.