In this test i'm mainly looking at performance for full body tracking. This clip only received minor cleanup on the legs, and a bit of hand-animation for the hands/head. This whole thing was done in the timeframe of a few hours... a large chunk of that was spent lugging my whole computer downstairs and plugging it into the living room so that I had space to move around.
A limitation of only using a single kinect camera is that it has no way of tracking you if you turn beyond 30-40 degrees away from the camera, and if your arms or legs overlap significantly it will have to guess where they actually are (which is often wrong).
I can do most of the simpler dialogue shots I need for Delura with the computer upstairs using mocap, but a little spring cleaning is going to be needed before I can do the stuff like shown in this video without hauling the compy downstairs.
kkots
Reminds me of how I was trying to make a stop-motion animation with puppets. I was limited in that I had no means of lifting them in air, and I had no greenscreen nor software for it. The only thing I could do was applying something sticky to the feet, so that they could at least walk. And their knees and elbows (and necks) wouldn't bend. I didn't want to make something limited, so I didn't make anything at all with those.
Conclusion: technology, if limited, can be used for limited purposes. Further those limitations, the technology can't be used.
Tanadrine-Studios (Updated )
Yeah, mainly the mocap is going to be combined with regular animation during production. The mocap is for simpler stuff (dialogue scenes, idle character motions, simple stepping, upper body motions, etc). Everything I'm doing with this mocap is interactive with the Lightwave and I can actually see the characters in the shots as they are created, unlike with almost all other mocap solutions :)
The Lightwave group is waiting for Microsoft to get off their duffs and expand the SDK to include multi-camera (or kinect 2) support.