Building Cities Out of Pictures

Researchers are working on technology to help create 3D models of buildings and places by using large collections of digital photos.
February 24, 2010, 8am PST | Nate Berg
Share Tweet LinkedIn Email Comments

With technology that processes huge amounts of digital image data, researchers at the University of Washington and Cornell University are able to quickly create 3D representations of buildings, neighborhoods and eventually entire cities. The technology is similar to a Microsoft application called Photosynth, but takes the process steps further.

"Photosynth collections are generally limited to dozens or hundreds of photos. The researchers wanted to push - or 'scale' - their technology to be able to handle tens of thousands or even millions of photos. They also wanted to use computer processing power to transform the photos into true three-dimensional images, or what they refer to as a 'dense point cloud.'

The visualization technology is already able to quickly process large collections of digital photos of an object like a building and render ghostly and evocative three-dimensional images. To do this they use a three-stage set of algorithms that begins by creating a 'sparse point cloud' with a batch of photos, renders it as a denser image, capturing much of the original surface texture of the object, and then renders it in three dimensions."

Full Story:
Published on Monday, February 22, 2010 in The New York Times
Share Tweet LinkedIn Email