Google updates Project Genie to build 3D worlds from Street View

Google has updated Project Genie with Street View integration. The AI can now convert panoramic images of real places into interactive 3D spaces in a matter of seconds. The tool runs on Google's models and makes it easier to build virtual worlds based on reality.

AI-processed from 3DNews AI; edited by Hamidun News
Google updates Project Genie to build 3D worlds from Street View
Source: 3DNews AI. Collage: Hamidun News.
Listen to article
Article Fact Sheet & Key Figures
ParameterDetails
Primary source3DNews AI ↗
Editor-in-Chief
Key metric #1Control the camera and explore the scene from every side
Key metric #2Interact with objects in the environment (open doors, move items)
Key metric #3Change lighting, weather and time of day in real time

Project Genie, Google's experimental 3D world generator, has received a significant update. The company has added integration with Street View panoramas, allowing the AI to create interactive 3D spaces directly from real-world locations.

How Google expanded Project Genie

The tool, built earlier this year on Google's models, now works with the Street View archive: decades of panoramas collected from around the world. This means any Street View frame can be turned into a playable, interactive 3D space in a matter of seconds.

Previously, Project Genie required users to upload a video or photo, which the AI analyzed and converted into a small three-dimensional world. The process was slower, and the result depended on the quality of the source material. Now the Street View integration simplifies the workflow: you pick a panorama and get a ready-made 3D space.

Street View covers millions of locations, from city streets to remote villages, so the tool's potential has grown sharply.

How the technology works

Project Genie uses a neural network approach to analyze a 2D image and build a 3D model with plausible physics. The AI understands depth, distances between objects, shadows and lighting. From this analysis it generates an interactive space where the user can move the camera, change the viewing angle and add elements.

One advantage of Google's approach is that the AI learns from real photographs, so the generated worlds look more natural than simple panorama-to-3D conversions. The level of detail is impressive, especially for street scenes with well-known architecture.

What the updated tool can do

Project Genie generates interactive 3D environments in which users can interact with their surroundings:

  • Control the camera and explore the scene from every side
  • Interact with objects in the environment (open doors, move items)
  • Change lighting, weather and time of day in real time
  • Add characters and dynamic elements
  • Export the result to game engines or 3D applications

The generated world stays compact. It is not a full-featured 3D space but rather an interactive scene that creates a convincing illusion of depth and volume.

Where it could be useful

The Street View integration opens up unexpected uses. Architects and designers can quickly prototype changes to real places: adding a building, redesigning a street, altering the landscaping. Game developers get an environment generator that saves weeks of manual modeling.

Tourism platforms will be able to offer interactive previews of locations instead of static photos. Instead of a gallery of images of a hotel room or restaurant, visitors will be able to "walk through" a 3D version. Companies such as Google Maps and Airbnb, along with virtual tour developers, are interested in such technologies.

What this means

Google is moving toward a world where reality and the digital merge automatically. Street View, once just a navigation aid, is becoming raw material for interactive 3D worlds. The trend points to a future where any place on Earth can be not just seen in a photo or video but explored interactively, without leaving home.

Story

Key Questions Answered

How Google expanded Project Genie?

The tool, built earlier this year on Google's models, now works with the Street View archive: decades of panoramas collected from around the world. This means any Street View frame can be turned into a playable, interactive 3D space in a matter of seconds. Previously, Project Genie required users to upload a video or photo, which the AI analyzed and converted into a small three-dimensional world. The process was slower, and the result depended on the quality of the source material. Now the Street View integration simplifies the workflow: you pick a panorama and get a ready-

How the technology works?

Project Genie uses a neural network approach to analyze a 2D image and build a 3D model with plausible physics. The AI understands depth, distances between objects, shadows and lighting. From this analysis it generates an interactive space where the user can move the camera, change the viewing angle and add elements. One advantage of Google's approach is that the AI learns from real photographs, so the generated worlds look more natural than simple panorama-to-3D conversions. The level of detail is impressive, especially for street scenes with well-known architecture.

What the updated tool can do?

Project Genie generates interactive 3D environments in which users can interact with their surroundings: Control the camera and explore the scene from every side Interact with objects in the environment (open doors, move items) Change lighting, weather and time of day in real time Add characters and dynamic elements Export the result to game engines or 3D applications The generated world stays compact. It is not a full-featured 3D space but rather an interactive scene that creates a convincing illusion of depth and volume.

ZK
Zhemal Khamidun — CPO at Alpina Digital, product manager of AlpinaGPT. Building AI products since 2019. Hamidun News is a pet project that grew into a production aggregator with 6,000+ readers.
✦ Unified AI Workspace · Nomad

Test Frontier LLMs & Autonomous Agents in One Workspace

Run Claude Opus 5.5, GPT-6, Gemini 3.1, and DeepSeek side-by-side in Nomad AI (nomadnet.ai) — unified model routing, deep research, and multimodal workflows under one subscription.

Try Nomad AI →Launch Nomad Agent
What do you think?
Loading comments…