Today’s insanity: The Crossing of the Uncanny Valley

Those of you who’ve been reading Utter Insanity blog for a while may remember that I wrote a post about the uncanny valley a while back. Well, ladies and gentlemen…it looks like we’ve touched down on the other side (although the accuracy of said touchdown relies on how well the model translates into movement). The image you see above is indeed CGI, and without the scary unhumanness of images we’ve seen that haven’t quite fully crossed the uncanny valley. In fact, it’s unbelievably photorealistic, and I suppose the scariest part of it is that she’s being rendered in real time. I’ve yet to see a video clip of this CGI woman moving, and that will be the telling bit (and if anyone locates such a video, please let us know in the comments–I’d like to write an update to this post).

So how is this done?

Obviously, new hardware is part of the solution. More processing power
has always meant more realistic visuals. However, there’s another
trick: a globe-shaped room that feature rapid high-definition
photography from all angles. These cameras can capture surface detail
to a level that surpasses human touch. These cameras operate so quickly
that to the naked eye, they appear as solid lights, when in fact they
are flashing on and off at fractions of a second. The information
captured by these cameras can then be interpreted into 3D data.

Impressive! We should start seeing video game intro sequences with this level of detail fairly soon, if the current state of computing power is anything to go by. And hot on the heels of that, we might start seeing movies that are so unbelievably real, that it’ll be almost–if not completely–impossible to tell the difference.

See more photos and read a more in-depth discussion about this new technology at Joystiq.

[Link: Joystiq - AMD Cinema 2.0 tech demo: real-time photo-realistic human models]