The promise and peril of using visual AI to study cities

Teaching AI to see the world more like we do

Our new paper analyzes the important ways AI systems organize the visual world differently from humans.

AI vs Human Expert Reasoning: Assessing Agreements in Building Typology Predictions based on Street View Imagery

arXiv:2607. 14756v1 Announce Type: new Abstract: This research investigates the potential of Vision-Language Models (VLMs) to infer building typologies: Construction, Current Use, and Storeys from Google Street View (GSV) images.

From Street View Imagery to Street Quality Indicators: Vision Language Inference for the Suburban 15-minute City

arXiv:2608. 20026v1 Announce Type: cross Abstract: Streetscape quality has become a central concern in contemporary urban planning, particularly within the framework of the pedestrian-friendly 15-minute city, where walkability and public-space quality are increasingly recognized as key determinants of urban performance.

360CityArena: A Realistic Virtual Urban Navigation Benchmark for Embodied Agents

arXiv:2608. 08814v1 Announce Type: cross Abstract: We present 360CityArena, a benchmark for evaluating the urban exploration capabilities of embodied agents within a photorealistic environment constructed from 360-degree videos.

Simulate real-world places with Project Genie and Street View

We’re expanding access to Google AI Ultra subscribers globally and introducing a new capability powered by Street View.

Jinhua Zhao named head of the Department of Urban Studies and Planning

An expert in behavioral science and transportation, Zhao combines these studies with AI and public policy to address some of the most urgent challenges facing cities.

AI agents create virtual playgrounds to help robots get crucial training data

“SceneSmith” system uses collaborative AI agents to create realistic 3D environments of places like kitchens, hotels, and living rooms, where robots can simulate everyday chores.

Introducing Activation Atlases

We’ve created activation atlases (in collaboration with Google researchers), a new technique for visualizing what interactions between neurons can represent. As AI systems are deployed in increasingly sensitive contexts, having a better understanding of their internal decision-making processes will let us identify weaknesses and investigate failures.

MindTopo reveals VLMs’ spatial reasoning abilities

A path, a fence, a knot. MindTopo sets a new benchmark for testing how AI understands topological relationships and highlights new opportunities to strengthen spatial reasoning and planning.

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

arXiv:2506. 16898v2 Announce Type: replace Abstract: Diffusion-based text-to-image models are increasingly used for urban analysis and scenario generation, but their geographic knowledge and representational biases remain poorly understood.

AI in abundance

Exploring the context of online images with Backstory

New experimental AI tool helps people explore the context and origin of images seen online.