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

TL;DR

This paper investigates the geographic biases and knowledge gaps in state-of-the-art image generation models when creating urban scenarios, revealing a bias toward metropolitan areas and entity disambiguation issues.

Contribution

It provides a systematic analysis of geographic biases in image generation models using synthetic images and embedding similarity metrics.

Findings

Models favor metropolis-like areas over rural regions.

Bias toward European-sounding place names causes disambiguation issues.

Models implicitly learn some geographic features of the USA.

Abstract

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 Fr\'echet 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.