3-D Models of Landmarks Stitched Together from Ordinary 2-D Pictures
A screenshot of a 3-D model of the exterior of the Coliseum, Rome, Italy.
CREDIT: Jan-Michael Frahm, UNC-Chapel Hill
Computer scientists have rolled out another version of photo-stitching software that automatically creates 3-D models of landmarks and geographical locations using ordinary two-dimensional pictures available through Internet photo sharing sites such as Flickr.
The technique creates the models using millions of images, processing them on a single personal computer (PC) in less than a day.
To demonstrate their technique, the researchers used the three million images of Rome available online to reconstruct all of the city’s major landmarks. It took less than 24 hours on a single PC using commodity graphics hardware. They also reconstructed the landmarks of Berlin in the same manner.
According to its creators, the process provides a far richer experience and is an improvement of more than a factor of 1,000 over current commercial systems, such as Microsoft PhotoSynth, and alternative techniques developed by other researchers in recent years.
"Our technique would be the equivalent of processing a stack of photos as high as the 828-meter Dubai Towers, using a single PC, versus the next best technique, which is the equivalent of processing a stack of photos 42 meters tall – as high as the ceiling of Notre Dame – using 62 PCs," said team leader Jan-Michael Frahm, a research assistant professor of computer science at the University of North Carolina at Chapel Hill.
"This efficiency is essential if one is to fully utilize the billions of user-provided images continuously being uploaded to the Internet," Frahm added.
One advantage of the 3-D models compared to viewing a video of a landmark is that the Internet photo collections used to construct them show the scene at different times and under different lighting and weather conditions, potentially creating a richer experience for viewers.
If video is available, however, the technology can utilize it as well, and using video shortens the processing time needed for reconstruction of the models.
Frahm said eventually the models could be embedded, for example, into common consumer applications such as Google Earth or Bing Maps, allowing users to explore cities from the comfort of their homes.
Other applications, such as geolocation, could prove useful to travelers.
"You might be able to take a picture with your cell phone of a monument that would not only give you information about that monument, identifying it from the image, but could also tell you your location more precisely than even GPS," Frahm said.
He also noted that the technology could be a building block for disaster response software. For example, an aircraft could be sent to take video of the aftermath of a hurricane, and the resulting 3-D model could be used to assess damage from a remote location, saving time and money.