A screenshot of the 3-D model of Rome's Colosseum, generated using several thousand Flickr photos. The black points surrounding the Coliseum indicate the vantage points from which photographs were taken. Image courtesy Build Rome in a Day project

Researchers at the University of Washington generated a 3-D model of Rome’s greatest landmarks in a day — and they did it by standing on the shoulders of Flickr users.

The researchers applied their algorithms to 150,000 Flickr images of Rome. It took a computer cluster containing 496 cores 13 hours to match common points in the images, sorting them into groups based on the landmark depicted. Another eight hours of computation time, and they had 3-D models of landmarks such as the Colosseum, St. Peter's Basilica, Trevi Fountain and the Pantheon.

The Building Rome in a Day project, which is still in progress, aims to build a parallel distributed system that can use Flickr photographs to reconstruct entire cities. According to the project website:

"The key contributions of our work is a new, parallel distributed matching system that can match massive collections of images very quickly and a new bundle adjust software that can solve extremely large non-linear least squares problems that are encountered in three dimensional reconstruction problems."

In addition to Rome, the researchers have generated simulations of Venice and Dubrovnik.

The results of the University of Washington team's work has already been featured in several media outlets, including Popular Science and a Seattle Times blog.

To see videos and images of the visualizations the researchers have generated so far, please visit their website.