Slashdot Mirror
Leaping the Uncanny Valley
reachums submits this glance at "the newest level of computer animation," intended to get past the paradoxical "uncanny valley" — that is, the way animated humans actually can appear jarring as the animation gets hyper-realistic. "This short video gives us a glimpse of what we can hope to see in the future of computer games and movies. Emily is not a real actress, but she looks like a real person, something we haven't truly seen before in computer animation."
There was much talk about the uncanny value when Final Fantasy: The Spirits Within came out after Square had promised for years that it would have realistic humans. A common criticism was that the human beings were real enough to inspire comfort for long enough that one would be then shaken by their lack of certain flexibility and the bloodlessness of their faces. Dr Aki was more creepy than sexy.
From what i understood, this is simply an easier kind of motion capture that works straight from video without the need for sensors etc. That's not the same as creative animation, you still need a real person talking and moving.
My appreciation of Douglas Adams is far deeper than yours.
That was pretty bad ass. Now do Sammy J!!
Not quite 100%, though. It still has the same problem as almost all previous attempts - the eyeblinks don't look right.
I don't know quite what it is - too slow? The eyelids always meet in the same place? - but it's the one thing that screams "fake" to me.
...many flesh-and-blood actors I've seen.
In a discussion elsewhere, someone stated that the facial animation was good, but the body movement was unrealistic. Since the body movement was actually a live actor, I'd say that this was analogous to a passed Turing test -- an observer couldn't tell which parts were animated and which parts were human. (It's a weak analogy, of course, since there was no interaction.)
Only the face is CG. The rest is a real actress.
So gluing an weird uncanny mask on an actors face will be the future of animation?
Why is it always some shitty blog that's linked instead of the original article?
Just as synthesizers were the end of "real" musicians, photography was the end of "real" paintings, etc.
Slashdot Burying Stories About Slashdot Media Owned
I'll let you know when I see something other than a postage stamp sized youtube video.
First off, they failed at getting passed the "uncanny valley". That video is still creepy looking.
Second, this isn't computer animation. It's just video processing. If you still need to do high resolution motion capture to produce your images, you haven't replaced the actor. You've merely edited their appearance in the performance. They didn't even bother to go so far as to take the captured motion and paste key bits of it together into the speech. They just had her sit there and say the whole thing, then "rendered" it.
Lame.
Motion capture a face and rerender it from the same viewpoint as a camera used to capture the texture and you'll trivially get something almost indistinguishable from the original. It's only a valid test if you change something significant: move the camera, change the lighting, change the facial features or change the performance.
-- SIGFPE
but it sure doesn't seem to be producing something of value, when there's a general level of distaste to what CGI's done to filmmaking. I've grown tired of paying my $13 to watch computer graphics fight each other on the big screen.
I still remember Titanic being the first time I've heard that the human mind has a built-in detector that alerts when they see animated humans, and fooling it is very difficult. Well, I watched Titanic and noticed right away when they showed animated humans, so it was still a long ways off from delivering what they promised.
I am amazed at the quality of this animation: Still, I could see there was -something- wrong with her, but could not put my finger on it. (this was of course also influenced since I -knew- she was fake before watching the vid).
Btw, here's a direct link to the video: http://www.youtube.com/watch?v=bLiX5d3rC6o
Be sure to tick the 'Watch in high quality' when the video opens (anyone knows a way to do that automatically in a link?)
When you shoot a mime, do you use a silencer?
The mouth is pasted in the face all crooked. Look at the mouth, it creeps the hell out of me.
Knowledge is power. Knowledge shared is power lost.
When they use different faces at the end, then clearly the technique is being used (and even if they had chose a more natural face it would have been obvious). But are they saying that the technique was in use for the entire video ?
If so - it has me fooled - there was a small glitch at one point, but nothing that would lead me to think it was a faked video until the end.
Nullius in verba
I'd say it's past the uncanny valley. That's not to say that I can't tell it's fake. She looks a little fake. Something is wrong-- her face is too still or something. But she doesn't look like a zombie. She's not distractingly creepy. That's all they're really shooting for at the moment, right?
looks like kevin costner will be out of a job soon. why pay millions for wooden actors with exactly 1 tone of voice? almost feel sorry for the guy.
I wonder if certain faces work better with this technology than others. Perhaps younger, smoother faces (like "Emily") work better than old, wrinkly faces, since they can get an accurate representation of skin texture without as much complexity.
Do stuffed animals instantly create a sense of revulsion? Not really else they wouldn't have been around for so long yet this is the ultimate uncanny valley item. As close to the living thing as you can get, fully posed as if it is alive, yet a rotting corpse nonethless.
If you ever dealt with real corpses you would know that they really ain't all this disgusting, it is so easy to get used to it that you might be temped to think that the so called natural revulsion is just media installed reaction.
If the uncanny valley really exist, then please explain realistic paintings that have been around for ages, artisit have tried for hundred of years to create realistic images of human beings and we admire their efforts without any sense of revulsion. Same with statues. Do we feel uneasy at madam Thussauds?
Yes we do NOTICE it when a seemingly realistic thing behaves unrealistic but I have the same sense when I see a car in a computer cut scene that doesn't obey the laws of physics and for instance slides.
It has nothing to do with the uncanny valley, if a real human being was holding a glass of water that didn't spill when tipped over you would get the same feeling.
We know how things work and when they don't we get upset. The trick that cartoons and such pull is that they say right up front by their looks that they are not real and therefor things don't have to work as we expect it.
That was the problem with Final Fantasy, it tried to be a human drama and then didn't use human emotions on the faces of the actors. IF it had been a pure action flick with no close-ups there wouldn't have been a problem. It wasn't the uncanny valley, it was just bad acting, if it had been done by humans who could act we would have felt the same.
MMO Quests are like orgasms:
You may solo them, I prefer them in a group.
Uncanny valley in a nutshell: Is it a "Good Robot" or a "Bad Human"?
But, there is an assumption about what is acceptable... what is the norm? At the moment, we're in a rapid transition phase. There are relatively few human-enough-like examples within our day-to-day existence. I would suggest that as these emulants (to coin a term) become more prevalent and pervasive, their familiarity will reduce the perception of their being bad.
We've come a long ways in the 35+ years since I used an ASR-33 Teletype over a 110-baud modem to a time-shared 8KB minicomputer. That sounds like a long time, and in some respects, it is. Today's generation has seen rapid advancements in game consoles, and even now, the best still appear really good, but still unreal. My guess is that in 5-10-20 years, when the visuals become even better, AND THERE HAS BEEN AN EXTENDED PERIOD OF FAMILIARITY, there will be less of a gap to leap. Not just because the visuals got better, but because we have become more familiar with them.
An aside: Look into the eyes of a young baby. Watch how they make eye contact, and don't let go. Watch how intently they examine you. That's setting up neurons and patterns of what is safe, good, bad, and everything else.
P.S. I wonder if the transition from the old black and white TVs to today's HDTV sets has run through a similar perception challenge?
They have another demo on their Front Page
And while it's extremely impressive, sadly it's definitely in the valley for me.
Face slanted to the side, blinking uneven. Really creepy.
"Who is the Journal of Quantum Physics going to believe?" --Stephen Hawking
Not to down play the achievement.
Now when you have a realistic looking virtual actor that works like this:
Character: Dorothy
Dialogue: Oh Auntie Em! There's no place like home!
Emotion: Overjoyed
Then we've got something.
Prisencolinensinainciusol. Ol Rait!
There is something downright wrong with the eyes. I can't put my finger on it, but it just looks creepy.
"To those who are overly cautious, everything is impossible. "
Yay ! Wonderful low-bandwidth youtube streaming video in all its glorious crap-quality !
The best way to show technical demos about photo-realism !
I can't wait to see the thumbnail sized 60%-quality jpeg screen caps, too !
I feel as much informed about the quality as when watching all those wonderful ads about hiddef screens on the TV.
---
Common, Image Metrics, can't you just post a descent hi-quality video file, so we can actually see what your technology looks like ?
"Sufficiently advanced satire is indistinguishable from reality." - [Tips: 1DrYakQDKCQ6y52z6QbnkxHXAocMZJE61o ]
would be playing Superman some years ago (thank $DEITY it didn't happen -- enough that he ruined DareDevil), I remember thiking oh, well, Chris Reeves is paralyzed from the neck down, and now Superman will be played by someone paralyzed from the neck up... :-(
people will laugh at this just like they laugh today at that "Men at Work" video.
stuff |
Just how much easier would it be to make James Bond with the same face for decades? Hell, you could make stunt doubles do all the acting, glue on a pretty face and be done with it. Replace them if they ask for to much money but keep the face going.
MMO Quests are like orgasms:
You may solo them, I prefer them in a group.
I can't wait till this technology used in pr0n!
Near the end of the vid, they have about two seconds of "real Emily".
After seeing this part, I'm really under impressed. They basically took a really hot chick and put some kind of software wireframe mask over her face and made her look exactly the same - only creepy.
When you can take a fat, ugly chick and make her look like real Emily - blog it.
I always appreciate people pushing the envelope, but this is just an alpha test.
If you can read this... 01110101 01110010 00100000 01100001 00100000 01100111 01100101 01100101 01101011
This doesn't leap the valley, it digs it deeper.
One of the creepiest things I've ever seen.
59 Comments & we've already killed PCWorld.com
There is a war going on for your mind.
Heck, she doesn't even look as real as Celine Dion, let alone a real person.
Help! I'm a slashdot refugee.
I wish I'd somehow had a chance to view this before knowing that it was a computer animation... say, a side-by-side comparison of a real and an animated person and a challenge to guess which was animated.
To me, "Emily" did not look real and did look uncanny. Actually, it reminded me of nothing so much as one of those videos where they replace a baby's mouth with animation so that it appears to be talking like an adult. It seemed to me that the animation's "mouth" was not stably positioned on its "face;" when the head turned, I perceived a change in the position of the mouth relative to the face. Something about the skin didn't look right, either.
Would I have accepted it as real if I were expecting "real?" Yes. But that's not the same thing.
Some years back I took part in an experiment to gauge something about necessary bit rates and algorithms to make synthesized speech sound real. What struck me forcibly was that, in this experiment, when you were listening to the best synthesized speech, if I'd had no standard of comparison I'd have said it was real. But when they switched to a real voice saying the same thing, there was the most amazing sensation, almost a tactile sensation of sound shaped by warmth and moisture. Only after you heard the real thing did the synthesized speech seem cold and mechanical.
"How to Do Nothing," kids activities, back in print!
Not just "very close"... it's motion capture, not animation. So, yes, it is pretty much exact. Anything "odd" you see in the face is just because you've been told it's animation. Jokes on you.
Meh.
Agreed, this is a bad test case. For me, it's all in the eyes. Final Fantasy had some ground-breaking stuff in it, but I can't get past the fact that everyone looks cross-eyed! With the technology they have, why is it so hard to focus the eyes?
This video minimizes this, as she is staring at the same point for the whole video, but you can still see it there as well.
Sooooo, now they can have actors act out scenes, then create digital versions that look exactly like the actors doing exactly what the actors did. Fascinating.
Because someone wants their shitty blog to get hits and hopefully cause said shitty blog to become immensely popular and profitable.
Meh.
Every Saturday Night Satirist will want one: "You can have my virtual talking head when you pry it/him/her from my cold dead fingers."
``Tension, apprehension & dissension have begun!'' - Duffy Wyg&, in Alfred Bester's _The Demolished Man_
I could tell from the beginning that the face was applied and the body was real. The face looked odd and strangely smooth. I've seen other systems do as well with the facial capture with a far better final result. The movements are getting close to real but it's still not a 100% and if you can't convince people on a low res clip I doubt it'll fool anyone at modern game res. The technology is improving but I hate to break it to everyone but it's still actor driven so what's the big deal? Better stunt shots? It's more impressive to see the movements on a non human character than on a human. It's harder to fool the eye with a human because millions of years of evolution have taught us to spot humans. I have seen some impressive facial work done lately but it's an expensive process and largely pointless. I still remember fifteen years ago critics seeing actor replacement as being the big thing computers had to offer. They have changed how films are made on every level and we still aren't up to replacing humans. Until you get rid of the capture step you aren't replacing actors you are using actors to drive avatars, period.
Now ugly people can be actors too!
How much is your data worth? Back it up now.
and hours of computer time, to make someone look *exactly* like themselves. Truly uncanny. And completely unimpressive, as they could just be, you know, lying their asses off about the whole thing.
If the actress under the fake face had looked completely different at the end, then that would have been impressive. Otherwise, who's to say they didn't just film the real actress the whole time, and claim to be digitally replacing her features while doing nothing of the sort.
I had a discussion with a friend some years ago about how long it would be before we could go into a video shop and ask for 'Rain Man', but with Arnold Schwarzenegger in both lead roles. I think it had been triggered by the idea that Sony had licensed the model human data based on Kevin Bacon in 'Hollow Man', as it had cost so much to digitise that they weren't going to use it just once. I seem to remember reading that a lot of the FX shots in Spider-Man 1 were done using that digital human, just with a Spidey skin, so there was a question about whether you could use the film in a game of 6 Degrees.
Assuming these guys are telling the truth, how long before actors start having their faces 'preserved' digitally at their peak, and still appearing as they were in their 20's or 30's decades later, even on a completely different body?
We all assume the human in the video is a woman. But wouldn't it be more impressive (and scary) if it were a man?
The world is made by those who show up for the job.
A Scanner Darkly.
It is by my will alone my thoughts acquire motion; it is by the juice of the coffee bean that the thoughts acquire speed
Look at her eyebrow movements and other gestures. They are too smooth and even. Real people don't do that.
If you measured how real people move and threw in some randomness on top of that, it would look a lot more realistic.
Within a few years, you won't be able to tell an SDTV-quality newsreader from a computer simulation in a 5-minute clip. Within a generation, it will be possible to do feature-film-length "live-action" movies that exist only in a computer, and the average viewer couldn't tell it wasn't live-action.
Knowledge is how to play a game, intelligence is how to win, wisdom is knowing what game to play.
For a look at the "uncanny valley" in the other direction, I recall someone posted this link to something about http://inventorspot.com/articles/girls_get_anime_look_with_extrawide_contact_lenses_16872">"anime eyes" contact-lenses in a story a couple of days ago and it certainly freaked a number of people out.
The World Wide Web is dying. Soon, we shall have only the Internet.
Well, a better question is if the uncanny valley really exists. Or rather, if it's really as simple as that valley, or we're actually looking at a more complex and multi-dimensional phenomenon.
And I'll attempt to build a framework to falsify it. It's a bit roundabout and I'll start by explaining the what and why of that framework, before all else. Bear with me, please.
First of all, before someone jumps in with the ever popular, "OMG, you're not worthy to question the high priests!" (err... "scientists"), the uncanny valley is just a hypothesis. A very compelling and well argued one, no doubt, but hardly a proven fact.
Second, before I get into the meat of the argument, the points chosen to represent it are highly debatable. E.g., is a zombie scary because of being close enough to the real thing to fall in the "uncanny valley", or because of the whole cultural meaning of death, undeath, corpses, etc?
When you look at each point individually, you can handwave and argue it to be wherever you want it, to support your hypothesis. It's called the Texas sharpshooter fallacy, after the fable of the sharpshooter who shot first and then painted a bullseye around the hole. You can "prove" anything in (pseudo-)science if you can do just that to the data: take a fuzzy and ill defined points and argue where they belong on your curve.
The "uncanny valley" paper does just that. We don't know the exact X coordinate on that graph for a zombie or a robot. It could be way right or way left, or whatever. So what really follows is that Mori decided a priori where they belong on that curve, and then places them at a point based on that. It's a textbook application of the Texas sharpshooter fallacy.
So what I'm going to do is an ad absurdum reduction of his curve.
I don't know the exact coordinates of any of my examples either, but, here's the important part: I don't need to pretend to. I'll just peg them between two other values, which, assuming the curve is correct, both fall in the valley or outside it, or some other position. Based on the reaction they caused, and, again, assuming that the curve were correct.
And due to the shape of the curve, if two points are in the valley, then everything between them is in the valley too. If two points are, say, both to the left of the valley, then a point between them should be on the left of the valley too. That is the important part.
So, let's build a counter-example: the FF movie was called a clear example of the Uncanny Valley. It's in the valley. Sony's Everquest 2 (particularly with the unnatural ambient bloom enabled) caused a similar reaction, and many euphemisms were used to describe just that: that that world looked disturbingly unnatural, especially if you pushed the graphics settings high enough. Classic example of entering the uncanny valley from the left, eh? So it's point 2 in that valley.
A point between them should, obviously, also be in the valley. That curve only has one dip, right?
Well, point #3 could be Oblivion. The graphics are better and more detailed than Sony's graphics in EQ, but don't even come close to the insane polygon counts and animations of the FF movies. It's between the two points. It should also be in the valley. It isn't. Nobody was repulsed by Oblivion's graphics. Or pick Crysis, or whatever newer high-end game, and you get the same curious behaviour. It ought to be in the valley, but it isn't.
Let's build another counter-example: so we're told that zombies are only repulsive because they're so close to humans as to fall in the uncanny valley. So logically, if you start with a zombie and move farther and farther away from human-like with it, eventually it exits the valley. Right? In fact, past a point it becomes outright _cute_ and appealing. Or ought to. I mean, that's the shape of that curve.
You probably realize already how absurd that statement is, but let's actually imagine it. Let's say we start with that corpse an
A polar bear is a cartesian bear after a coordinate transform.
1. I'm glad it has been formally recognized that computer-animated humans look creepy. "Uncanny Alley". Good call and so true.
2. This isn't animation. It's digital film with an advanced form of cut & paste. --Which isn't to say that it's not cool or that it doesn't open up some new nifty options for film-makers. But animation? Come on.
They put real moving lips on animated faces back on some awful show back in the 70's, and nobody should have been proud to call that "animation" either. Basically, no animator is ever going to break the barrier in "Uncanny Alley" because photo-realism is not what animation is about. Animation is about using abstract generalizations to capture the impression of human qualities. Photo-realism simply doesn't belong in the world of hand-painted art. Animator's hands are not wired up to cameras; they're wired up to these wondrous pattern and abstraction machines which exist forever in the boundless world of dream logic. And thank-goodness for that, or we'd be a race of cold and un-feeling robots. Ick.
-FL
... was too low in resolution to see anything. A higher resolution video would've been more helpful.
More importantly, as other posters have said, this still requires humans doing the original. This is an apples and oranges argument when comparing this to animation from scratch.
Come on!! that is so fake
her lips are not off, resolution is so bad if you maximize it that she off altogether, lipsync is bad because video quality is bad.
You people are so easy to fool.
at the end it's only special effect, any good studios can overlap those special effects over anyone's face.
you people should get out more.
i'm guessing some of you believe they are actual real lifesize transormers out there since they looked so real.
Oh, wait a minute... this ISN'T animation, it's basically a wireframe model placed directly over the face. It basically is the real thing.
Meh.
I'm sick of hearing that perfectly realistic CG will mean the end of real actors, even if they are just saying it to get publicity.
Real actors will never be replaced as long as the people who watch films do so at least in part for the people on screen: people they admire; people they envy; people about whom they may fantasise.
I know (or at least hope) the makers of this virtual person don't really think they'll do away with actors (voice and live theatre are two barriers to that at the moment), but I would like someone to change that particular stuck record.
The GooTube thumbnail looked better, but the higher resolution shot on image-metrics.com looked fake. Also, the voiceover still requires a living human.
Every time technology progresses further in terms of realism we get this exact same scenario.
What happens every time is:
people use games as excuses for things, blaming the games for being "too close to real life" for totally unattributed things (see: GTA lately?)
Additionally we get people scared/confused by the additional realism that occurs as well and spread FUD.
I really wonder what will help when tv is higher resolution than real life, aka futurama?
Is this not somehow missing the point?
Is this her?
If so, good but a little way to go yet :)
Is there any actual animation (can you make Emily blow a kiss, stand up, do something the actor didn't do), or is this just fancy rotoscoping?
The only thing new here is that the equipment required to do the motion capture has been reduced to a single video camera. The facial movements are not being generated by a computer, merely copied from an actor so it's still nowhere near a believable simulation of a human face.
const int one = 65536; (Silvermoon, Texture.cs)
SJW, n: "Someone I don't like, and by the way I'm a fuckwit" - AC
I saw this last week at Image Metrics's booth at Siggraph.
Image Metrics is really about capturing facial motion and not so much about rendering.
It looks very real, only the face is weird.. in fact, only the face is synthetic (possibly just remorphed).
When I realized that it was a re-animated face on top of an actual real world video I felt a bit cheated 8)
"La presi e te la pagai (480.000 Lire)"
Broken link in parent, try this
Real Emily lips have more specularities, and her skin is more detailed than the virtual counterpart. The face positioning looks a bit strange as well. BTW, this is very interesting. People complain they have pasted a virtual version of the same face, but that's missing the point that they could have pasted any imaginable face using the same recorded expressions. It's not perfect, but still quite impressive.
Image Metrics calls this "performance transfer technology". It's not really animation; it's more of a scheme for pasting face A onto actor B. Quite a bit of this already goes on; often, when you see a stunt performer's face on screen, the face of the principal has been transferred to the image of the stunt performer. With this new technology, that can be done without matching camera angles or going through the whole "dots on the face" makeup ordeal.
The video of "Emily" is not some from-scratch animation. It's very closely based on live footage. This is digital image make-up, not animation. "The end of actors?" Hardly. Feh.
Tom Swiss | the infamous tms | my blog
You cannot wash away blood with blood
The person in the video is Emily O'Brien a professional actress. You can find a much better video of Image Metric's work on this page of her website
So they make a 3D model of Emily's face (using a 3D scanner, presumably), then they film Emily moving her face, then they deform the model to match Emily's facial expressions, then they superimpose the model on Emily's head.
Er... what for?
At best they'll end up with something identical to the original (but they don't - the model doesn't wrinkle properly and sometimes the tracking is slightly off - you can see her face "float" relative to the hairline and ears).
I could understand the point if they could take expressions from one person's face and replicate them on another person's face (which is something you can do with motion capture - and some clean-up work). But obviously they can't do that automatically, or they would have done it for the demo.
I can see this kind of technology being useful to disguise the transition between an actor's real face and a 3D face (which will later be deformed by hand, or morphed into some creature, etc.), but the demo is so limited (camera doesn't move, the 3D face is almost identical to the real face, etc.) that it seems a long way off from being an alternative to motion capture and manual tweaking. This is like showing some (supposedly) revolutionary new GPU by making it print "Hello World" on the screen. If the technology is so great, why such a limited demo?
What about that funky Replicant teddy bear from Blade Runner? That was all the way IN the Uncanny Valley.
BTW the girl on the video in the article...FAIL. Very, very, VERY creepy.
Knowledge is power. Knowledge shared is power multiplied.
I thought it would be a story about the female sexual organs.
"Vagina: The Eerie Canal"
remember when Boopsie had her body digitized?
The nose (the nostrils in particular) don't move, which results in a disconnect between the mouth and eyes.
The masses are the crack whores of religion.
Is they are trying to make a perfect looking human...humans are defined by their imperfections. When they airbrush real humans too much it winds up looking fake.
They need to add human imperfections to the CGI models to pass the uncanny valley test.
Porn directors will now be able to use even the skankiest starlets, and with this new technology, you won't see ANY pimples on their ass or breast augmentation scars! Heck, they could even have _guys_ provide the motion capture for the starlets instead... .
I was going to say 'tits or gtfo' but then I realised this was slashdot, not 4chan...
magine just how much it would be worth to paramount to have a young Kirk, McCoy and Spock available.
Not only that, but how about brand new episodes of Gilligan's Island or Hogan's Heroes? Or how about a proper final season or two of Farscape, or Firefly?
Although... Voices may still be a problem. How are we doing on believable voice synth?
When our name is on the back of your car, we're behind you all the way!
Broken link in parent, try this
"Since no amount of cosmetic surgery will make actual human eyes larger, some girls are trying another way to up their cute quotient: extra-wide contact lenses!"
Well, there is the crazy shit known as "eye tattooing". It's still a young procedure and I don't know if they can blend a tattoo that close to the iris.
Oh, say does that Star-Spangled Banner entwine / The myrtle of Venus with Bacchus's vine?
You take an actor, have them deliver a series of lines or perhaps play an entire character role, and then you use that performance to sync up with some facial imaging software so that a computer can play back the perforamce? That sounds like double-work to me. Sounds pretty f*ckin' useless too, but what the heck do I know? As an actor, I'd be totally offended to be told, "Oh by the way, we're going to overwrite your performance with some software because you don't look like the actual character." Well then why would you pick that actor/actress in the first place?
This seems like someone has spent alot of time and money to attain a goal simply because they can. I am unimpressed....close to revolted, actually.
Why do people on slashdot feel the need to use words like cognitive dissonance, a psychological/clinical term rather than just expressing how it makes you feel?
Jesus was a compassionate social conservative who called individuals to sin no more.
The shark still looks fake.
Confucius say "Uncanny valley not such a difficult problem for porn."
Fascism trolls keeping me up every night. When I starts a preachin', he HITS ME WITH HIS REICH!
A quick check of IMDB says that the article has it all wrong. "Emily" is a real person and actress, the only parts that were simulated were only the crappy looking (although technically very difficult) modifications made at the end. According to the credits at the end of the video, her name is Emily O'Brien (imdb) So I guess all the "fake" and "awkward looking" gestures she made in the video weren't proof it was fake, just proof that she's a bad actress.
Let's make some horror video games where the people in it are creepy enough to really freak people out.
The demo looks fantastic .. the only problem I had was that there was some loss of definition around the eyes. Otherwise, wow. Double wow.
My belief is that this mechanism would make it very very very difficult for a super-intelligent race to "fool" us into thinking one of their own in disguise was one of us.
You could perhaps argue that if they were that intelligent that they could pull it off - but I doubt that to be the case - because it seems that these type of biological traits - be they reflexes, implules, etc. - are so refined in the structure of biology - that almost no amount of "intelligence" could overcome them. Furthermore, with something as complicated as the subtlties in not just look, but smell, sound and especially behavior - it would be an impossible task to pull off.
Obviously - you could argue that they could with enough sophistication, etc. - but this is just my $0.02.
This happened to me one Saturday night :(
Disney created a "show" called, if I remember, Turtle Talk at their Epcot theme park. It's basically an animated turtle on screen that talks, and responds to the audience in real time. Apparently there's an actor controlling the eyes, mouth, movement, and providing the vocal responses of the character on the screen.
It had a quite a bit of an uncanny valley feel to it because it was so close to human movement and looks on a turtle. If they made the turtle an animated human that responded to the audience like that, my guess is that many of the kids in the audience would be freaked out to the point of leaving the room.
Anyways, my personal experience with uncanny valley. Turtle Talk highly recommended.
This is the type of thing that is going to usher in a new era of dangerous computerized interaction. Voice/Gesture recognition + Emily = Lonely Computer Geeks wet dreams. A woman that will talk and interact with you. Later, for everyone, a computerized friend. Gee, it's not hard enough to get regular people to use verbal communication nowadays, let's add another layer of complexity to that by allowing them to program how their "realistic" friends interact with them. I for one say nay.. I'll stick with people. TYVM
Ok, so it's not quite at the same level, but my Logitech webcam will stick a hat or beard on my face in real time, or completely replace my video with video of a shark or a cat or a stick figure whose mouth, eyes and expressions mimic mine. Way, way cheesier looking effect, but hey it's just a webcam!
Regarding the extended period of familiarity, I've found that I'm less and less aware of effects in movies. I used to instantly see something as an effect. Now it's entirely possible for me to watch an effects movie without even thinking that something is fake.
I'm sure the same thing is happening to me regarding animated actors. The more uncanny valley I see in video games, the less unusual the valley seems.
I think it's conceivable that the valley could close up without any additional advanced being made. I might just get used to it and not see it as abnormal.
It's like fake boobs. The more women there are who have fake boobs, the less likely I am to even think that they might have fake boobs.
Cow Cube
Has nothing to do with Uncanny valley, well, almost..
This is amazing stuff, also something which can be used for future computer animations:
http://www.garry.tv/?p=623
I sometimes wonder where all those "magical algorithms" come from.
I confess that, at least at this res, I would have been fooled hands down; that is, viewing Emily cold. No way would I have twigged that this is CGI in a blind test. IMHO knowing it was an animation beforehand queers the game a bit. Hard to say if any perceived funniness is projection or perception.
That said, with all the possible faces art and imagination could muster, Couldn't they have made her a little hotter? Or maybe chosen the face of a star long since gone?
And that dress. Yikes! No taste. Absolutely no taste. She must have started her career at Microsoft.
"No fear. No envy. No meanness." Liam Clancy
My patented idea is utilizing this technology to revolutionize movies in the future. You will be able to insert your family members, friends, favorite actress into the role of whatever Hollywood release comes out. The acting would look the exact same but you could get a different face. Say you would like to see your own face instead of Christian Bale in Batman, no problem. This is the future of the entertainment business.
Does God treat us as servants or friends? Check my homepage.
I don't think we've yet seen anything that the uncanny valley hypothesis would cover. This is a real human being, with a real voice and a real body, with a computer rendered (not animated) face that is actually not very convincing in the higher resolution video.
A robot programmed to emulate human emotions, looks, and language will represent the first truly creepy descent into uncanny valley; something that appears real on the surface and yet leaves you with the uncomfortable feeling that there is "something wrong", something you can't put your finger on.
It's a recording of a woman with some graphics over it? That's what it sounds like (and doesn't sound impressive)
If Google really cared they would fix Android Chrome to reflow text, instead of discriminating
While there's leaps that have been made in computer animation that are obvious even in a low resolution YouTube video, it still has the same problems that Polar Express has...a lack of expression. "Emily"'s facial expression was still pretty bland and robotic, and seemed to be lacking the range of motion seen in a real human. Unless it was an oversight that the animators missed in their demo...but I doubt it.
That said, we're definitely getting closer...
Charisma is the measure of someone's ability to lie with a straight face.
It's more convincing than...many flesh-and-blood actors I've seen.
So when they get it perfected maybe this will mean that they can hire good actors instead of good looking actors and then use the computer to pretty them up.
The other advantage will be that the celebrity salaries will probably end up being more reasonable over time since studios can own the digital likeness and use whomever they want to animate it. Of course this will likely mean trouble since now the actors/actresses will actually get paid a reasonable salary based on how well they can act....
Erm, ya? Taxidermy often is creepy, especially creative taxidermy.
Quack, quack.
This "proprietary software" sounds a lot like a farking video camera with "makeup mode". I mean, how is it so different from video that has been digitally edited for tweakage??? If it starts with a real actor/actress, requires filming, and the end product is 99% (your definition on percentage may vary from mine) from the "film"... where is all this supposed CG??
I thought Kerrigan got them all long before they got home?
Unless....
The WMDs are psi emitters!!1
If Tyrell couldn't do it, what makes you think we can?
This has crossed the lowest point of the valley but is just beginning to climb back out.
It looks like real video because it is real video. Wow.
I love 30 Rock.
(You can see the scene that quote is from at http://www.mediawithabrain.com/2008/04/25/30-rock-tackles-uncanny-valley-with-worlds-first-porn-video-game if you watch the second video.)
With enough exposure to non-human reactions, you pitiful humans lose your sensitivity to this. Why do you think we gave the world Anime and GTA. By the time our warriors have reached your planet, you will be ripe for.... *ahem*
I mean, of course, you are right my fellow human. We could easily see through such disguises. Come let us enjoy a chilled liquid at the local poison dispensary together.
An even bigger problem will be making robots that can convincingly pass for human while physically in their presence and trying to feign one-on-one communication. Have you ever noticed that somehow, something just kind of clicks, and you *know* you've made eye contact with someone... and you know that THEY know, too? They might be far away, in a moving vehicle, looking at something else (or just generally looking around), but every now and then "it" happens... you make random, fleeting eye contact with a stranger.
My theory is that it's due to the fact that your eyes are always moving (if your eye were perfectly still, you wouldn't be able to see, because rods and cones derive most of their information from CHANGES rather than instantaneous sampled state). I'm guessing that the pattern of movement appears random, but somehow the part of your brain responsible for background signal processing is able to recognize that movement pattern in the eyes others, and tries to synchronize itself to it. Neither person is intentionally trying to do it, or is even aware of it, but their brains -- through visible eye movement -- are actively negotiating the equivalent of a handshake... and when it happens, a metaphorical "datagram" gets sent to your conscious brain letting you know that you've "locked on" to another person. When you're intentionally talking to someone, it lets you know that you have their attention. When it unexpectedly happens at some random moment when you're just gazing out at the horizon, it can be awkward and uncomfortable.
It's why if you're trying to hide, the worst thing you can possibly do is try to watch what's going on nearby. You might be in the dark shadows, or behind a large object with little more than a hole big enough to see through... but somehow, if someone happens to gaze in the right direction, and their eye detects the movement pattern of an eye somewhere nearby, they're going to immediately feel like something is amiss, even if they don't immediately realize what just happened. If their gaze crosses the gaze of another person who's looking at something entirely different, it might just be a feeling of unease. It's why looking for a lost person or animal is easier than looking for a lost object, at least if you're close enough to potentially make eye contact, Looking for a misplaced object, your brain has to process everything it sees, and constantly do pattern-matching. With people and animals, it's kind of like they're emitting a short-range beacon that allows you to randomly gaze around, but get "that feeling" whenever eye contact occurs, signaling that some area merits further visual inspection.
Anyway, getting back to the Uncanny Valley, it'll be interesting to see what impact the ability to feign eye contact by robots will have. A robot with no eye contact seems creepy in a "dead" kind of way. Would a robot that "almost" managed to maintain eye contact be MORE comforting, or creepier still? Would the "comfort" factor depend upon whether the person interacting with the robot KNEW they were interacting with a robot? Or would making "almost correct" subconscious eye contact with a robot send chills down the person's spine, setting off subconscious alarms to let them know, "DANGER! Something here isn't quite right!", regardless of whether the person KNEW it was a robot?
THAT demo is for presenting what their facial capture and animation system can do.
You know... like taking a live actor, record his/hers performance WITHOUT adding any markers AND turning that video into a 3D animated face.
No need for modeling. Just have the actor ACT and record that.
Mit der Dummheit kämpfen Götter selbst vergebens
I worked with Image metrics on a project last year. The mocap stuff they sent us was nice, but they baked all the animations into the vertexes so we had a hell of a time trying to sync it up with the rest of the character. We finally figured out where they hid all their animation keys. It wasn't on any properly named node either. Only marginally annoying I have to say. They really need to learn their place in the production pipeline. Since I'm probably going to have to be dealing with them again very soon.
I have nothing compelling to say
I'd "digitise" her "uncanny valley" any day
Well, ok. Maybe. Still, even without that, the point can still be made with other examples.
I mean, for some you don't even need two anchor points. It's enough to start with something on the left and move even more left, or stuff like that. The curve being what it is, it's still possible to make a prediction and test it.
E.g., a zombie still doesn't move out of the valley if you make it even less human, as I was describing.
E.g., ok, so they say that cartoon characters are appealing and create empathy because they're on the peak on the left side. Fair enough. So moving it farther to the left (i.e., towards even less human), should at best make them even more attractive, and at worst still remain above zero. Because there is no other dip below zero to the left on that graph.
So... let's start from a talking bunny like Buggs Bunny. Hmmm? A zombie, maggot-infested, rotten-corpse-eating, talking bunny, stretching his arse like the goatse guy? I think it just got pretty disgusting.
A polar bear is a cartesian bear after a coordinate transform.
She has no wrinkles. Her smiles look totally fake. And what's with the ghoulish makeup?
It wasn't the same fish each time, it wasn't the same place each time, it wasn't even the same time(of day) each time - I would be swimming & sightseeing, stop for no apparent reason, start observing closely, and there would be a large-eyed fish watching me.
Thanks for making me reconsider my initial position - what's that old expression? It's not the things we don't know that get us in trouble, it's the things we know that aren't so.
Hmmm. Your ideas are intriguing to me and I wish to subscribe to your newsletter.
-Apu, Trying to act like he's not an alien (From India).
So we've got stuffed animals around the house, some of them on the bed, and they're more likely to be feline (lions, tigers, pumas, etc.) rather than bears. My previous cat decided that all of them were pillows for cats to lie down on, though he'd chew the whiskers off of them.
My new cat (who's about 4 years old) generally feels that way, but one day he hopped up on the bed and saw a tiger that's about the size of a housecat, and he freaked. He cautiously snuck up to it, worried it was going to attack him, until he got close enough to sniff it and could be sure it wasn't real. After that he's been ok with it. Also there's a cheetah that's about half his size that purrs when you squeeze it (cheetahs are the only large cats that purr), and he'll go over and knead on it repeatedly to make it purr.
Bill Stewart
New Fast-Compression-only CPR http://preview.tinyurl.com/dy575ks
If the quality gets to the 'undetectable' level, you could be placed on-camera in a criminal act, for instance, or alternatively, supply a (fake, but albeit difficult to disprove) 'video alibi'.
This may provide Groklaw with new meat in the future...let's wait and see.