Trafy
Research

Simulate real-world places with Project Genie and Street View

We’re connecting Project Genie with nearly 20 years of Google Street View imagery so you can create new worlds anchored in reality.

Google DeepMind·May 19, 2026·4 min read·Original source ↗
Simulate real-world places with Project Genie and Street View

Simulate real-world places with Project Genie and Street View

May 19, 2026

·

Share

x.com

Facebook

LinkedIn

Mail

Copy link

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

Diego Rivas

Group Product Manager, Google DeepMind

Jonathan Herbert

Principal Product Manager, Maps

Nicole Segaran

Associate Product Manager, Google Labs

Share

x.com

Facebook

LinkedIn

Mail

Copy link

Sorry, your browser doesn't support embedded videos, but don't worry, you can download it and watch it with your favorite video player!

Your browser does not support the audio element.

Listen to article

This content is generated by Google AI. Generative AI is experimental

[[duration]] minutes

Voice

Speed

Voice

Speed 0.75X 1X 1.5X 2X

Genie is our general-purpose world model capable of generating diverse, interactive environments. Since launching, Genie has become a foundational tool for research, enabling agents to learn and reason in complex virtual settings and even helping Waymo simulate hyper-realistic road environments.Now, we’re taking a leap forward by connecting Genie’s generative power with the real-world imagery of Google Street View, allowing our models to anchor themselves in reality. This expansion of Genie’s capabilities can provide a virtual environment for AI agents or robots to navigate and interact with the complexities of the real world.Today, we’re launching this new Street View grounding capability within Project Genie, our experimental prototype. With this upgrade, you'll be able to leverage real-world imagery to explore your favorite spots, or reimagine them with a creative twist. We’re also expanding access to Project Genie to more people around the globe.

Select the “Ocean World” style to scuba dive with schools of fish around places grounded in the real world.

Street View: ground your worlds in real placesWhen creating imaginative worlds in Project Genie, you can now also base them on real places. Just tap the Maps pin to choose a place in the U.S. and optionally select a style for your world, like “Desert Sands” or “Stone Age.” Then, describe your character — like your favorite animal, comic book hero or even a claymation monster — and Genie will use this information to create an imaginative world with its starting location tied to Street View’s real-world imagery. This capability is powered by Maps Imagery Grounding, the same technology developers use to create stunning AI visuals with Street View.Want to see the Golden Gate Bridge under the sea? Select the “Ocean World” style to scuba dive with schools of fish around the bridge. Or, if you want to explore what the iconic Fort Worth Stockyards in Texas might have looked like in the 1920s, select the “B&W film” style to see a world with saloons, vintage cars and trading posts.Street View imagery in Project Genie is available now for places in the U.S. with plans to expand to more places over time.Project Genie: now available with Google AI UltraStarting today, Project Genie — including the new Street View capability — is gradually rolling out to all eligible Google AI Ultra $200 subscribers globally (18+). Try creating today with Project Genie.Project Genie is still an experimental research prototype in Google Labs, so we're working behind the scenes to make the details even sharper and more accurate. You can read more about our progress and current limitations on our website.

Get more stories from Google in your inbox. Get more stories from Google in your inbox.

Email address

Your information will be used in accordance with Google's privacy policy.

Subscribe

Done. Just one step more.

Check your inbox to confirm your subscription.

You are already subscribed to our newsletter.

You can also subscribe with a different email address

.

POSTED IN:

Related

Learning When to Trust via Selective Context Preference OptimizationResearch

Learning When to Trust via Selective Context Preference Optimization

Language models increasingly condition their answers on external signals, and a single misleading one can turn a correct answer wrong. The obvious remedy, training models to resist such signals, hides a failure mode: a model that ignores all context looks robust yet is useless when the context is worth trusting. We recast the problem as selective trust and introduce MIST, a human-annotated benchmark that renders each reasoning item under four matched conditions (clean, misleading, correct-context, and irrelevant-context), together with SC2W, a paired metric counting how often a misle

arXiv (cs.AI) · Aug 6, 2026
4 min
Learning When to Trust via Selective Context Preference OptimizationResearch

Learning When to Trust via Selective Context Preference Optimization

Language models increasingly condition their answers on external signals, and a single misleading one can turn a correct answer wrong. The obvious remedy, tr...

Papers with Code · Aug 6, 2026
1 min
Tracing the Heart: An Evidence-Linked Pipeline for Heart-Failure Feature EngineeringResearch

Tracing the Heart: An Evidence-Linked Pipeline for Heart-Failure Feature Engineering

Electronic health record (EHR) feature engineering is a major bottleneck in clinical research and AI, accounting for 39-45% of data scientists' workload. This is especially pronounced in heart failure, which affects an estimated 6.7 million U.S. adults and requires integrating fragmented EHR data with disease-specific, guideline-based clinical reasoning. Existing rule-based and large language model (LLM)-based approaches offer only partial automation with limited maintainability and evidence traceability. We developed the Nimblemind Multi-Agent System (nMAS), an evidence-linked, rubr

arXiv (cs.AI) · Aug 6, 2026
4 min