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

• URL: http://arxiv.org/abs/2506.16898v1
• Date: Fri, 20 Jun 2025 10:43:22 GMT
• Title: AI's Blind Spots: Geographic Knowledge and Diversity Deficit in Generated Urban Scenario
• Abstract summary: We generated 150 synthetic images for each state in the USA and related capitals using two state-of-the-art models for image generation.<n>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.
• Score: 4.315451628809687
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• GeoDiv: Framework For Measuring Geographical Diversity In Text-To-Image Models [42.84755778627983]
  Text-to-image (T2I) models are rapidly gaining popularity, yet their outputs often lack geographical diversity, reinforce stereotypes, and misrepresent regions.<n>We introduce GeoDiv, a framework leveraging large language and vision-language models to assess geographical diversity along two complementary axes.<n>GeoDiv reveals a consistent lack of diversity and identifies fine-grained attributes where models default to biased portrayals.
  arXiv  Detail & Related papers  (2026-02-25T17:08:43Z)
• Where Do Images Come From? Analyzing Captions to Geographically Profile Datasets [33.86868726260716]
  We geographically profile large-scale multimodal datasets by mapping image-caption pairs to countries based on location information extracted from captions using LLMs.<n>We find that the United States, the United Kingdom, and Canada account for $48.0%$ of samples, while South American and African countries are severely under-represented with only $1.8%$ and $3.8%$ of images, respectively.
  arXiv  Detail & Related papers  (2026-02-10T13:36:16Z)
• The Best of Both Worlds: Integrating Language Models and Diffusion Models for Video Generation [53.837937703425794]
  LanDiff is a hybrid framework that synergizes the strengths of autoregressive language models and diffusion models.<n>Our architecture introduces three key innovations: (1) a semantic tokenizer that compresses 3D visual features into compact 1D representations through efficient semantic compression; (2) a language model that generates semantic tokens with high-level semantic relationships; and (3) a streaming diffusion model that refines coarse semantics into high-fidelity videos.
  arXiv  Detail & Related papers  (2025-03-06T16:53:14Z)
• Uncovering Regional Defaults from Photorealistic Forests in Text-to-Image Generation with DALL-E 2 [5.534517268996598]
  Regional defaults describe the emerging phenomenon that text-to-image (T2I) foundation models are prone to over-proportionally depicting certain geographic regions. In this work, we introduce a scalable evaluation for uncovering such regional defaults. Our findings underscore a need for further investigation into the geography of T2I generation and other forms of generative AI.
  arXiv  Detail & Related papers  (2024-10-03T19:07:12Z)
• The World Wide Recipe: A community-centred framework for fine-grained data collection and regional bias operationalisation [3.505416621482746]
  We introduce the World Wide recipe, which sets forth a framework for culturally aware and participatory data collection.<n>We analyse bias operationalisation to highlight how current systems underperform across several dimensions.<n>We find that these T2I models generally do not produce quality outputs of dishes specific to various regions.
  arXiv  Detail & Related papers  (2024-06-13T18:00:00Z)
• Sat2Scene: 3D Urban Scene Generation from Satellite Images with Diffusion [77.34078223594686]
  We propose a novel architecture for direct 3D scene generation by introducing diffusion models into 3D sparse representations and combining them with neural rendering techniques. Specifically, our approach generates texture colors at the point level for a given geometry using a 3D diffusion model first, which is then transformed into a scene representation in a feed-forward manner. Experiments in two city-scale datasets show that our model demonstrates proficiency in generating photo-realistic street-view image sequences and cross-view urban scenes from satellite imagery.
  arXiv  Detail & Related papers  (2024-01-19T16:15:37Z)
• Inspecting the Geographical Representativeness of Images from Text-to-Image Models [52.80961012689933]
  We measure the geographical representativeness of generated images using a crowdsourced study comprising 540 participants across 27 countries. For deliberately underspecified inputs without country names, the generated images most reflect the surroundings of the United States followed by India. The overall scores for many countries still remain low, highlighting the need for future models to be more geographically inclusive.
  arXiv  Detail & Related papers  (2023-05-18T16:08:11Z)
• Social Biases through the Text-to-Image Generation Lens [9.137275391251517]
  Text-to-Image (T2I) generation is enabling new applications that support creators, designers, and general end users of productivity software. We take a multi-dimensional approach to studying and quantifying common social biases as reflected in the generated images. We present findings for two popular T2I models: DALLE-v2 and Stable Diffusion.
  arXiv  Detail & Related papers  (2023-03-30T05:29:13Z)
• Implementing and Experimenting with Diffusion Models for Text-to-Image Generation [0.0]
  Two models, DALL-E 2 and Imagen, have demonstrated that highly photorealistic images could be generated from a simple textual description of an image. Text-to-image models require exceptionally large amounts of computational resources to train, as well as handling huge datasets collected from the internet. This thesis contributes by reviewing the different approaches and techniques used by these models, and then by proposing our own implementation of a text-to-image model.
  arXiv  Detail & Related papers  (2022-09-22T12:03:33Z)
• Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language [49.82293730925404]
  Large foundation models can exhibit unique capabilities depending on the domain of data they are trained on. We show that this model diversity is symbiotic, and can be leveraged to build AI systems with structured Socratic dialogue.
  arXiv  Detail & Related papers  (2022-04-01T17:43:13Z)
• DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models [73.12069620086311]
  We investigate the visual reasoning capabilities and social biases of text-to-image models. First, we measure three visual reasoning skills: object recognition, object counting, and spatial relation understanding. Second, we assess the gender and skin tone biases by measuring the gender/skin tone distribution of generated images.
  arXiv  Detail & Related papers  (2022-02-08T18:36:52Z)
• Generating Physically-Consistent Satellite Imagery for Climate Visualizations [53.61991820941501]
  We train a generative adversarial network to create synthetic satellite imagery of future flooding and reforestation events. A pure deep learning-based model can generate flood visualizations but hallucinates floods at locations that were not susceptible to flooding. We publish our code and dataset for segmentation guided image-to-image translation in Earth observation.
  arXiv  Detail & Related papers  (2021-04-10T15:00:15Z)
• Urban2Vec: Incorporating Street View Imagery and POIs for Multi-Modal Urban Neighborhood Embedding [8.396746290518102]
  Urban2Vec is an unsupervised multi-modal framework which incorporates both street view imagery and point-of-interest data. We show that Urban2Vec can achieve performances better than baseline models and comparable to fully-supervised methods in downstream prediction tasks.
  arXiv  Detail & Related papers  (2020-01-29T21:30:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.