Soon you’ll be able to transform your standard 2D outdoor images into a more lively 3D image with Fotowoosh, a new service that’s just getting started. What’s great about it is that it only requires one image to get the 3D end result, unlike other services that typically require multiple photos.
Right now, the only way you can get your foot in the door at Fotowoosh is by signing up for a beta invite (here). All you have to do is enter in your name and an email address. From there you’ll get an email telling you that when it’s launched, you’ll get an invitation into the beta program.
For now you’ll have to be satisfied by their sample collection. In order to view the 3D models, you’ll need a browser plug-in because it uses VRML (explanation here) so that you can interact with the photos.
Also interesting is that this originally started out as a project of Derek Hoiem who’s a PhD candidate at Carnegie Mellon University. His project page actually made the front page of Digg 174 days ago. Hoiem explains it as a system that:
“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 estimate 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.
I’m not sure how fast this technology will take off in it’s current state. If a method is created where people can interact with these photos without any additional plug-ins for the browser, that would definitely help.