Slashdot Mirror

Software like Canoma from the now-defunct Metacreations would let you create 3D models from 2D images in the mid-to-late 90s. I also remember reading about people using Viz ImageModeler to convert images from video to models even though the software is also designed for still images - the users would just capture those frames they needed to create the 3D model.

The only thing "new" about this is using video as the input without having to grab the individual frames yourself.


Never let reality temper imagination

How does Auto stitch's tech compare to commercial programs like Stitcher?

I have a set of three Canon ZR500's that I'm planning to use in a rig that will record video from the top, right and front view of a moving target simultaneously. However, there are going to be a number of limitations to overcome with such a setup.

Luckily, it seems RealViz will soon be releasing a new software package, called Movimento, that claims to be able to obtain motion capture data from video of events taken from multiple camera angles. While this new software should definitely make things easier for me, it also appears that this software may be able to use video taken from non-stationary cameras as well. As long as there is simultaneous footage of a single event taken from two or more camera angles, the software should work.

But until Movimento is released, it seems manually rotoscoping motion using a rig like mine may work best for the time being.

REAL VIZ has been doing this stuff for years. They even have a few movies under their belt where their software has been used. http://www.realviz.com/

Note that this is a different thing from the one mentioned in the article. To do this you keep the camera at one point and rotate it, prefferably around the nodal point of the lens. To do the thing described in the article you keep it pointed in the same direction and at the same distance from the page and move it around.

REALVIZ Stitcher and some other panorama programs can also stitch togeather images of a flat object, like the article describes, but you must make sure that the camera remains at the same distance from the page and pointed in the same direction. I think some sort of stand is required. Hopefully with this new software you can get good results without a stand.

There is REALVIZ ImageModeler.

The technology of deriving 3d geometry information from 2d images is typically known as image-based rendering. Gabe Newell (head of Valve Software) said that this is one of the technologies they didn't have enough time to get into Half-Life 2. It was first demonstrated in The Campanile Movie and has since been used for special effects purposes in movies (including the Matrix). It is very impressive, not only for its ability to generate the geometry from the images, but also its way of generating perfect distortionless texture mapping for said geometry.

To lump all computer vision together and say "it's not there yet" is phooey! There are lots of problems in vision, and they do get solved, but those problems are all specific-- you can't use a red-light-runner system to do facial tracking...