Image Metrics and the Uncanny Valley
Many of you have heard of the Uncanny Valley. (For those of you who haven't, here's a quick quote from Wikipedia: "as a robot is made more humanlike in its appearance and motion, the emotional response from a human being to the robot will become increasingly positive and empathic, until a point is reached beyond which the response quickly becomes that of strong repulsion. However, as the appearance and motion continue to become less distinguishable from a human being, the emotional response becomes positive once more and approaches human-to-human empathy levels.")
I just came across a video showing off a completely computer generated figure that appears to pass that valley. There are still a few tiny rough edges - note the occasional over-extended lips (the "I just got braces" look) - but overall the effect is astounding. Gives me high hopes for future games - I'd love to know if this was being used for Heavy Rain, for example.