From Pixels to Places: A Systematic Benchmark for Evaluating Image Geolocalization Ability in Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Lingyao, Yu, Runlong, Hu, Qikai, Li, Bowei, Deng, Min, Zhou, Yang, Jia, Xiaowei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918504857337856
author Li, Lingyao
Yu, Runlong
Hu, Qikai
Li, Bowei
Deng, Min
Zhou, Yang
Jia, Xiaowei
author_facet Li, Lingyao
Yu, Runlong
Hu, Qikai
Li, Bowei
Deng, Min
Zhou, Yang
Jia, Xiaowei
contents Image geolocalization, the task of identifying the geographic location depicted in an image, is important for applications in crisis response, digital forensics, and location-based intelligence. While recent advances in large language models (LLMs) offer new opportunities for visual reasoning, their ability to perform image geolocalization remains underexplored. In this study, we introduce a benchmark called IMAGEO-Bench that systematically evaluates accuracy, distance error, geospatial bias, and reasoning process. Our benchmark includes three diverse datasets covering global street scenes, points of interest (POIs) in the United States, and a private collection of unseen images. Through experiments on 10 state-of-the-art LLMs, including both open- and closed-source models, we reveal clear performance disparities, with closed-source models generally showing stronger reasoning. Importantly, we uncover geospatial biases as LLMs tend to perform better in high-resource regions (e.g., North America, Western Europe, and California) while exhibiting degraded performance in underrepresented areas. Regression diagnostics demonstrate that successful geolocalization is primarily dependent on recognizing urban settings, outdoor environments, street-level imagery, and identifiable landmarks. Overall, IMAGEO-Bench provides a rigorous lens into the spatial reasoning capabilities of LLMs and offers implications for building geolocation-aware AI systems.
format Preprint
id arxiv_https___arxiv_org_abs_2508_01608
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle From Pixels to Places: A Systematic Benchmark for Evaluating Image Geolocalization Ability in Large Language Models
Li, Lingyao
Yu, Runlong
Hu, Qikai
Li, Bowei
Deng, Min
Zhou, Yang
Jia, Xiaowei
Computer Vision and Pattern Recognition
Image geolocalization, the task of identifying the geographic location depicted in an image, is important for applications in crisis response, digital forensics, and location-based intelligence. While recent advances in large language models (LLMs) offer new opportunities for visual reasoning, their ability to perform image geolocalization remains underexplored. In this study, we introduce a benchmark called IMAGEO-Bench that systematically evaluates accuracy, distance error, geospatial bias, and reasoning process. Our benchmark includes three diverse datasets covering global street scenes, points of interest (POIs) in the United States, and a private collection of unseen images. Through experiments on 10 state-of-the-art LLMs, including both open- and closed-source models, we reveal clear performance disparities, with closed-source models generally showing stronger reasoning. Importantly, we uncover geospatial biases as LLMs tend to perform better in high-resource regions (e.g., North America, Western Europe, and California) while exhibiting degraded performance in underrepresented areas. Regression diagnostics demonstrate that successful geolocalization is primarily dependent on recognizing urban settings, outdoor environments, street-level imagery, and identifiable landmarks. Overall, IMAGEO-Bench provides a rigorous lens into the spatial reasoning capabilities of LLMs and offers implications for building geolocation-aware AI systems.
title From Pixels to Places: A Systematic Benchmark for Evaluating Image Geolocalization Ability in Large Language Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.01608