« Your Libraries: Study Tables in Honnold/Mudd | Home | US Government Searches with Google »
Sci-Fi Wednesday: Photographs into 3-D
Carnegie Mellon researchers have developed a computer program that can create a 3-D models based on the content of a single photograph. The process of taking a two dimensional image and converting it into a 3-D model was not something that was always deemed possible, however:
Now, however, researchers in Carnegie Mellon University's School of Computer Science have found a way to help computers understand the geometric context of outdoor scenes and thus better comprehend what they see. The discovery promises to revive an area of computer vision research all but abandoned two decades ago because it seemed insoluble. It may ultimately find application in vision systems used to guide robotic vehicles, monitor security cameras and archive photos.
Read the rest.
View enlargment of the above photo.
View animation of the 3-D model.
— michael | June 14, 2006 05:29 PM | Random bits
