Hi, I came across an article from a while back about a technology demonstrated at Siggraph 2002 called Performace Capture "cross-mapping", developed through the Disney Human Face project: Creating Virtual Performers What caught my eye was that this technique seems to capture facial performance without reflective markers and uses very few cameras (only two in the example from the reading). The process is described:

Quote: The resulting footage, when scanned into the computer, was subjected to software analysis. While Disney understandably considers the details of this technique extremely proprietary, in essence what it does is track pixels. It looks at the photographed image in both views from the two cameras as each pixel moves from one view to the other. Every pixel making up the face is a target for this optical flow analysis.

The details, as they said are proprietary, so I guess its not surprising that I can't find much more information on this. Mostly I find a lot of references to the film Polar Express, which from what I have read, used reflective markers. Anyway, it seems that in 3 years time someone would know a little more about the specifics of Disney's cross-mapping technique? The article mentions the possible application to gaming, and think about it; the near perfect re-creation of facial expressions on digital characters using 1 normal camera and no reflective markers. Knowing that the new XBox will include a camera as a peripheral, I think there is some awesome potential here. Any thoughts?

Woah, I doubt if this is anywhere close to real-time.