AI's Blind Spots: Geographic Knowledge and Diversity Deficit in Generated Urban Scenario

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Beneduce, Ciro, Luca, Massimiliano, Lepri, Bruno
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908414888640512
author Beneduce, Ciro
Luca, Massimiliano
Lepri, Bruno
author_facet Beneduce, Ciro
Luca, Massimiliano
Lepri, Bruno
contents Image generation models are revolutionizing many domains, and urban analysis and design is no exception. While such models are widely adopted, there is a limited literature exploring their geographic knowledge, along with the biases they embed. In this work, we generated 150 synthetic images for each state in the USA and related capitals using FLUX 1 and Stable Diffusion 3.5, two state-of-the-art models for image generation. We embed each image using DINO-v2 ViT-S/14 and the Fréchet Inception Distances to measure the similarity between the generated images. We found that while these models have implicitly learned aspects of USA geography, if we prompt the models to generate an image for "United States" instead of specific cities or states, the models exhibit a strong representative bias toward metropolis-like areas, excluding rural states and smaller cities. {\color{black} In addition, we found that models systematically exhibit some entity-disambiguation issues with European-sounding names like Frankfort or Devon.
format Preprint
id arxiv_https___arxiv_org_abs_2506_16898
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AI's Blind Spots: Geographic Knowledge and Diversity Deficit in Generated Urban Scenario
Beneduce, Ciro
Luca, Massimiliano
Lepri, Bruno
Artificial Intelligence
Computer Vision and Pattern Recognition
Computers and Society
Image generation models are revolutionizing many domains, and urban analysis and design is no exception. While such models are widely adopted, there is a limited literature exploring their geographic knowledge, along with the biases they embed. In this work, we generated 150 synthetic images for each state in the USA and related capitals using FLUX 1 and Stable Diffusion 3.5, two state-of-the-art models for image generation. We embed each image using DINO-v2 ViT-S/14 and the Fréchet Inception Distances to measure the similarity between the generated images. We found that while these models have implicitly learned aspects of USA geography, if we prompt the models to generate an image for "United States" instead of specific cities or states, the models exhibit a strong representative bias toward metropolis-like areas, excluding rural states and smaller cities. {\color{black} In addition, we found that models systematically exhibit some entity-disambiguation issues with European-sounding names like Frankfort or Devon.
title AI's Blind Spots: Geographic Knowledge and Diversity Deficit in Generated Urban Scenario
topic Artificial Intelligence
Computer Vision and Pattern Recognition
Computers and Society
url https://arxiv.org/abs/2506.16898