I think we are on the verge of surpassing the what animators term as the ‘uncanny valley’:
For many years now, animators have come up against a barrier known as “uncanny valley”, which refers to how, as a computer-generated face approaches human likeness, it begins take on a corpse-like appearance similar to that in some horror films.
As a result, computer game animators have purposely simplified their creations so that the players realize immediately that the figures are not real.
The animation above is being done by Image Metrics (who are behind popular computer/video game Grand Theft Auto). We’re still not able to do this on-the-fly. Massive amounts of computations are required to calculate and control every little movement – every little twitch of the eye, the sneer, the muscles that contracts under the skin, etc.
But with chip technologies and architecture developing, it’s certainly not a pipe-dream to envision some day in the very near future where this becomes common place. What does it mean for us in the real world when we cannot distinguish the real from the fake? At a massive, ubiquitous level?
Really amazing animation – check out Times Online for a more comprehensive article.