An animation company has finally managed to create a computer-generated human that most watchers can't distinguish from a real person. Forget the clunky CG characters in most animated movies today - in a few years, you could be watching animated films that are almost indistinguishable from "live-action" ones. Click through to watch a slightly disturbing video.
The video actually uses a motion capture of a human actor to create a life-like animation. Image Metrics, whose animations were used in the Grand Theft Auto game, has developed a sure-fire way of making human faces look believable: apparently it's all about the eyes, and the little assymetries of the human face. There's a lot more fine control over the details in this new system, according to chief operating officer Mike Starkenburg:
There's always been control systems for different facial movements, but say in the past you had a dial for controlling whether an eye was open or closed, and in one frame you set the eye at 3/4 open, the next 1/2 open etc. This is like achieving that degree of control with much finer movements... For instance, you could be controlling the movement in the top 3-4mm of the right side of the smile
My question is, how long is it before we're all having video chat with slightly idealized animations of our friends? [London Times via Technovelgy]
DISCUSSION
how about we watch this in HD?
[rcpt.yousendit.com]
and here is an interview with some othe the Image Metrics people
[media.fxguide.com]
a someone who is working with Image Metrics right now I can tell you that their technology is extremely impressive.
the Image Metrics process is pretty simple...
and it's all dependent on the rig...if you build a rig that is capable
of the appropriate range of expression and capture the performance you
want, Image Metrics can generate animation that will drive your rig
with a level of detail that is really impressive.
the 'Emily' clip is, from an animation standpoint, is just
about the best I've seen...most of the criticisms, however valid, have
been about the tracking and shading...and the manner in which clip is
presented puts the viewer in an inappropriate mind set right off the
bat.
This demo, at least from my point of view (again as someone who is
working with IM right now) is a very impressive demo of the sort of
'base line' results that IM can deliver, a digital recreation of a
human facial performance...where it goes from there is up to the
client...take the actor's performance and put it on an 'aged' version
of her face, or on a different face etc.
I can't talk about what we're doing, but I can say that the results we
are getting are pretty remarkable, and we're doing some fairly extreme
stuff.
The real question here is about scale and cost effectiveness...
can an animator, given a rig that is capable of the appropriate range
of expression, produce a performance that is as good or better than
what IM has demonstrated with 'Emily'?
the answer is, of course, yes.
but can it be done is the same amount of time? = $
can it be revised as quickly? = $
can the animation be re-targeted to another character?
the question 'can something like this ever replace real actors?' is a valid one, and technology like this (and others) will
replace actors - not your Harrison Ford's etc but extra's had better
find ways to suplement their income...crowds are already being replaced
digitally and soon CG will be able to replace 'background' actors (the
other cops in the police station etc). Where this stuff really shines
(and where it will be used more an more in the coming years) is in
performance augmentation, The Curious Case of Benjamin Button is a good example (they're using Mova [www.mova.com]).
As an in-house test, and as a promotional clip this could have been
presented more effectively, but the underlying technology represents
the 'cutting edge' of digital performance.