Immersive virtual copies of the world, built by algorithms, for architecture, real estate, and beyond.

Get a Demo


Geopipe gives you detailed models of the real world in an instant. Simply select an area in our web interface, choose the level of detail you need for your application, and download your model in industry-standard file formats.

Geopipe's models can be used directly in the applications you already know how to use. Whether you need clay-like massings to visualize a new design in context, or realistic models for static renders and interactive walk-throughs, Geopipe helps you complete projects faster, by saving the time and money you would otherwise spend collecting reference materials and modeling the site by hand. Request a demo () or contact us.

  • Geopipe model configured for massed detail and rendered with lighting in an external program.
  • Geopipe model configured for realistic detail and rendered with lighting in an external program.
  • A large-scale view of several square miles of Geopipe's generated model of Manhattan, containing thousands of textured buildings and trees set on accurate terrain.


Geopipe builds clever algorithms to turn 2D and 3D data into highly detailed 3D virtual models.

Our system ingests and analyzes big geographic and numeric data, including satellite photos, maps, laser scans, and much more. We work with 2D and 3D data from public and private sources, and the more data we have, the more accurate our models become.
We apply machine learning ("deep learning") and algorithmic analysis techniques to understand the structure of the real world as represented in the data. Geopipe's system builds a semantic model of the world, representing not only what it looks like, but what's in it, from the ground to trees to the locations of individual windows in building facades.
By processing the data within a distributed system running in the cloud, we can rapidly analyze data and reconstruct whole cities in a matter of hours. Because we generate these models ahead of time, and update them as often as we have new data, you can immediately download models cropped from existing cities through our web interface.


Geopipe's founding team have a decade of collaborative history. Their complementary technical skills in distributed systems, interdisciplinary simulation and modeling, and machine learning makes Geopipe's technology possible.

Christopher Mitchell, Ph.D.

Christopher Mitchell, Ph.D.

Founder and Chief Executive Officer

Dr. Christopher Mitchell completed his Ph.D. in Computer Science at NYU, specializing in distributed systems, having previously earned an M.S. in Computer Science and an M.E. and B.E. in Electrical Engineering. Trying to put New York City into Minecraft piqued Christopher's interest in making immersive copies of the real world.

Thomas Dickerson

Thomas Dickerson

Founder and Chief Science Officer

Thomas Dickerson is a fourth-year Ph.D. candidate in Computer Science at Brown University, and holds a B.S. in Computer Science, Mathematics, and Physics. His research centers on applying the algorithmic lens to interdisciplinary problems. Thomas's interest in semantic modeling of built environments stemmed from a desire to automatically simplify models of real-world landmarks while preserving their iconic features.

Contact Us

Want to learn more about Geopipe, or request a demo of how we can help you finish projects faster, get you accurate massings, and make your renders more visually compelling? Drop us your details: