Quantcast Image Metrics and the Uncanny Valley - Ozymandias

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.

Share this post: email it! | bookmark it! | digg it! | live it!

Comments

Shep said:

Sadly, it's not a "completely" computer-generated figure. I read an article about the creation of this video a while ago, and it seems that only the face is computer generated - it's been superimposed on a live action body (the same live footage that the expressions were originally captured from, which is why it's such a seamless match!) - you get a better idea of just how much is live action, and how much is CGI, when they flip through alternate textures near the end of the video. The stuff that isn't appearing with freaky textures (i.e. most of the screen) is the original live action footage. But... let's face it... we all knew that hair and cloth was *far* too good to be cgi, right? ;)

The subtitles about the clip being a "wholly computer-generated animation" aren't on the original Image Metrics footage. I think somebody downstream of them has exaggerated the content somewhat ;)

Nice technique, all the same...

# August 19, 2008 2:52 PM

Ozymandias said:

Ah - very interesting... didn't know it wasn't entirely CG. Makes one wonder how much of the uncanny valley is derived from facial animations vs. the entire combination of all motion/animation across the whole body.

Well, one can hope we eventually get there!

# August 19, 2008 4:05 PM

Steve said:

On this topic, I saw this posted elsewhere:

rocketonblog.blogspot.com/.../beware-of-uncanny-valley.html

:P

# August 19, 2008 10:45 PM

Rafoca said:

Heavy rain is really looking pretty good, but I guess that is due to the fact on that style of game is easier to have great graphics.

I doubt if it were like GTA it would have those great graphics!

BTW, nice video :D

# August 20, 2008 12:10 PM