Simulate real-world places with Project Genie and Street View

2026-05-19 · Source: Google DeepMind News · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Robotics & Autonomous Systems, Emerging Technologies & Innovation · Depth: Novice, medium

Summary

Google DeepMind has expanded Project Genie, its general-purpose world model, by integrating it with nearly 20 years of Google Street View imagery. This new capability, launched on May 19, 2026, allows users to generate diverse, interactive virtual environments anchored in real-world locations. Project Genie, previously used for AI agent learning and Waymo's hyper-realistic road simulations, now enables users to select a U.S. location via a Maps pin, apply creative styles like "Ocean World" or "B&W film," and describe a character to populate the scene. This "Maps Imagery Grounding" technology facilitates reimagining places like the Golden Gate Bridge underwater or the Fort Worth Stockyards in the 1920s. Access to Project Genie, including this new feature, is gradually rolling out globally to eligible Google AI Ultra \$200 subscribers aged 18 and above.

Key takeaway

For AI Engineers developing simulation environments or Creative Technologists building immersive experiences, Project Genie's integration with Street View offers a powerful new tool. You can now ground your virtual worlds in real-world locations, applying diverse styles and custom characters. Explore this experimental prototype to accelerate agent learning, enhance autonomous driving simulations, or create unique interactive content, leveraging Google's extensive imagery for unprecedented realism and creative freedom.

Key insights

Project Genie now integrates Street View to create imaginative, interactive virtual worlds grounded in real-world locations.

Principles

• AI world models can anchor generative content in real-world data.
• Real-world imagery enhances virtual environment complexity.
• Generative AI supports diverse creative and research applications.

Method

Users select a U.S. location via a Maps pin, choose a stylistic theme (e.g., "Desert Sands"), and describe a character. Genie then generates an interactive world based on Street View imagery.

In practice

• Generate virtual environments for AI agent training.
• Create hyper-realistic road simulations for autonomous driving.
• Reimagine real-world locations with creative stylistic overlays.

Topics

• Project Genie
• Google Street View
• AI World Models
• Virtual Environment Generation
• Maps Imagery Grounding
• Autonomous Driving Simulation

Best for: Computer Vision Engineer, AI Scientist, Research Scientist, Creative Technologist, AI Engineer, Robotics Engineer

Related on AIssential

• Simulate real-world places with Project Genie and Street View — Project Genie now integrates Google Street View to create interactive, reality-anchored virtual environments for AI and creative exploration.
• What happens when you combine Nano Banana with Gaussian splat tours? — Combining Gaussian splats with generative AI enables interactive spatial reimagining of real-world 3D environments.
• Google Maps is about to get a big dose of AI — Google's new generative AI features enhance enterprise geospatial analysis and visualization across its mapping platforms.
• Google’s Genie world model can now simulate real streets with Street View — Google DeepMind integrates Street View with Project Genie to create interactive, real-world-anchored simulations for diverse applications.
• Project Genie | Shine and Seek — Google's Project Genie generates interactive 2D worlds from text or image prompts, building them in real time.
• Google pairs its Genie world model with Street View to create explorable AI worlds based on real places — Google's Genie model uses Street View data to create interactive AI worlds for agent training and simulation.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Google DeepMind News.