Wednesday May 21, 2008 Make3D
|
Make3D converts your single picture into a 3-D model, completely automatically. |
To quote their web site:
It takes a two-dimensional image and creates a three-dimensional "fly around" model, giving the viewers access to the scene's depth and a range of points of view.
How does it work?
It uses powerful machine learning techniques to learn the 3-D structure of a scene as a function of the (single) image features. The team at Stanford University, led by Ashutosh Saxena and Andrew Y. Ng has made the code available online; see more details here.
Here's a gallery of their public 3-D generated images.
You can also download their source code and learned parameters (needed for running code).
I thought I'd give it a try, but just via their web site. I uploaded an image taken in Monterey in February last year.
I was informed that conversion is a batch process, I was #11 in the queue, and that I'd get an email when processing was complete.
That was 11 hours ago. Hmm.
Maybe I should download their source code, build it and try it myself. It could be quicker.
( May 21 2008, 03:18:15 PM PDT ) [Listen] Permalink
Comments are closed for this entry.
![[ Registered ]](http://www.diarist.net/registry/button.gif ){kind=small}
