AI's Blind Spots: Geographic Knowledge and Diversity Deficit in Generated Urban Scenario
This work addresses biases in AI-generated urban scenarios, which is an incremental contribution to understanding diversity deficits in image generation for geographic applications.
The study evaluated the geographic knowledge and biases of image generation models FLUX 1 and Stable Diffusion 3.5 by generating 150 synthetic images per U.S. state and capital, finding that models show a strong bias toward metropolis-like areas and have entity-disambiguation issues with certain names.
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.