- Thu Jun 07, 2007 12:09 am
#231621
I think it's a different animal from qtvr - it's the ability to automatically organize images into a 3d space....
In other words, you could go onto google images someday, type in 'eifel tower' and photosynth could analyse all the iamges available and position them in 3d relative to one another. Pretty cool thing.
"A Photosynth experience begins with nothing more than a bunch of digital photos. They might all have been taken by one person, or they might be a mixture of images from many different cameras, shooting conditions, dates, times of day, resolutions, and so on.
Each dot represents an extracted feature
Each photo is processed by computer vision algorithms to extract hundreds of distinctive features, like the corner of a window frame or a door handle. Photos that share features are then linked together in a web. When the same feature is found in multiple images, its 3D position can be calculated. It's similar to depth perception - what your brain does to perceive the 3D positions of things in your field of view based on their images in both of your eyes. Photosynth's 3D model is just the cloud of points showing where those features are in space
"
47 photos totally
so I'll have to wait 
- By choo-chee
- By Mark Bell
- By Forum Moderator