« The 3D VuCAM™ - High Performance 3D Binocular from StereoVision Imaging, Inc. | Main | article on "Vladimir" home-made ViewMaster reels »

Tech Crunch reports on Fotowoosh: Turn Any Picture into a 3D Image?

flat_train2.jpgamtrak.gif

"When you upload an image to Fotowoosh, their software tears it apart and distinguishes the sky, ground and vertical elements within the photo, then cuts and folds it into a 3D model:"

Our system automatically constructs simple “pop-up” 3D models, like those one would find in a children’s book, out of a single outdoor image. The system labels each region of an outdoor image as ground, vertical, or sky. Line segments fitted to the ground-vertical boundary in the image and an estime of the horizon’s position provide the necessary information to determine where to “cut” and “fold” in the image. The model is then popped up, and the image is texture mapped onto the model.

"This is the creation of Derek Hoiem, a PhD candidate in Robotics at Carnegie Mellon University." - from the TechCrunch website

For the complete article, go here.
For the Fotowoosh site, go here.

TrackBack

TrackBack URL for this entry:
http://www.ny3d.org/cgi/mt/mt-tb.cgi/62

About

This page contains a single entry from the blog posted on April 19, 2007 8:25 PM.

The previous post in this blog was The 3D VuCAM™ - High Performance 3D Binocular from StereoVision Imaging, Inc..

The next post in this blog is article on "Vladimir" home-made ViewMaster reels.

Many more can be found on the main index page or by looking through the archives.

Creative Commons License
This weblog is licensed under a Creative Commons License.
Powered by
Movable Type 3.33