Google DeepMind Connects Street View to Project Genie World Model
Google DeepMind has connected its Project Genie world model to Google Street View’s 280 billion images, letting users explore AI-generated simulations of real locations. Announced at Google I/O, the feature is rolling out to Google AI Ultra subscribers in the US, with Waymo already using Genie 3 to train self-driving cars on rare scenarios.
Integrating Generative World Models and Real-World Data
DeepMind's Project Genie, its general-purpose system for creating interactive environments, now leverages more than 280 billion images captured across 110 countries and all seven continents. This integration allows users to navigate AI-generated simulations of real places in real time, such as a snowy New York City block or a sunlit London street.
From Research Preview to Consumer Product Google DeepMind's Street View Integration: Bridging Real and Simulated Worlds (2026 Update)
Google DeepMind has taken a significant step forward in bridging the gap between real-world environments and AI-generated simulations with its latest Project Genie update. By integrating Google Street View's vast library of 280 billion images, users can now explore and interact with AI-created recreations of cities and towns around the globe. This real-world data enhances the realism of Genie's simulations, making them invaluable tools for robotics developers and providing a novel way for the general public to experience familiar locations virtually.
The expansion of this technology promises to accelerate advancements in autonomous vehicles, robotics, and more. Waymo, for instance, is already utilizing Genie 3 to train its self-driving cars on rare events, leveraging the detailed Street View data to improve the accuracy and adaptability of its simulations. This simulation-to-reality pipeline is crucial for ensuring that robots and AI systems operate effectively in the real world.
While impressive, the Street View integration is still in its experimental stages. The generated environments, while visually stunning, lack the physics awareness and realism of actual locations. However, as the technology matures, it holds the potential to revolutionize how we interact with and understand virtual spaces.
Read the full article Google DeepMind plugs Street View into its world model, and you can explore simulated cities todayGenie 3, the latest iteration, initially appeared as a research preview in August 2025. In January 2026, DeepMind opened access to Google AI Ultra subscribers in the US. The Street View integration is now available to some Ultra users in the US, with global expansion planned for the coming weeks.
Applications and Impact
The feature serves two primary audiences: robotics developers who use it to train agents in simulated environments mirroring actual locations, and general users who can explore for fun. Waymo already utilizes Genie 3 in its simulators to train on rare events, enhancing the realism of their simulations by grounding them in real-world Street View data.
This simulation-to-reality pipeline is crucial for bridging the gap between what robots learn inside computers and how they perform once deployed. Companies like Nvidia and Cadence are also racing to achieve this, with DeepMind's approach offering a distinct path by layering generative models on top of real-world imagery.
Limitations
While impressive, the Street View integration remains experimental. The generated environments resemble video games more than photographs, and the model lacks physics awareness.