3-Sweep 3D Modeling -- New Tool?

[Sigma]

Not sure how I feel about this but I'll post it over here anyway. Seems like a useful tool for quick results and mockups but lacks the necessary attention to detail issues that CG requires.

 

Original: http://gamasutra.com/view/news/199842/Watch_the_intriguing_3Sweep_3D_modelling_technique_in_action.php

 

Video

http://www.youtube.com/watch?feature=player_embedded&v=Oie1ZXWceqM

 

A group of computer science professors is working on a new interactive 3D modelling technique, which can easily read information from various photos, and turn the objects into 3D models in just seconds.

The '3-Sweep' technique, as demonstrated in the above video, takes three mouse strokes which define the three different dimensions of an object. The first two sweeps define the object's profile, while the third sweep finds distinct outlines, and reads the object's shape along its main axis.

This defines a 3D body which will snap to the object in the photo, and can then be rotated, adjusted and generally played around with.

Notably, the video describes numerous instances in which the algorithm would not work, including when there is a non-ideal perspective, or when an object has a fuzzy, non-readable edge. No information is as-of-yet available on when this technique might be made available for public use.

Edited September 9, 2013 by Sigma

[Thrik]

I can definitely see this being used a lot for sequences in TV shows where they have 'animated photos' where different layers move around independently. I don't even know how they do those things normally but this would probably make it easier. The tool even seems to do Photoshop-esque smart image filling so there's something behind the object if you move it.