Hollywood Eyes Uncanny Valley In Animation
MELISSA BLOCK, host:
From NPR News, this is ALL THINGS CONSIDERED. I'm Melissa Block.
MICHELE NORRIS, host:
And I'm Michele Norris.
Whether or not "Avatar" wins at the Oscars this Sunday, the film's high-tech wizardry has already won praise and drawn record audiences. But no film has yet achieved the ultimate breakthrough, navigating the so-called uncanny valley that's digitally creating a realistic human character. WNYC's On the Media producer Jamie York explains why trying and missing the mark can lead to box office disaster.
JAMIE YORK: In 2001, DreamWorks was paying approximately $60 million for an animated movie about a green ogre named Shrek. And the animation brain trust tasked with making this $60 million investment pay dividends was well on their way. Lovable, if grotesque green ogre - check. Donkey sidekick that cracks wise - check. Fantastic world for everyone to inhabit - check. There was just one problem.
(Soundbite of movie, "Shrek")
Mr. MIKE MYERS (Actor): (as Shrek) Once upon a time, there was a lovely princess.
Mr. LAWRENCE WESCHLER (Writer, Wired Magazine): When they showed it to an audience of children, the children started crying and freaking out because there was something wrong.
YORK: That's Lawrence Weschler who wrote about this incident for Wired Magazine. It's true. The animators of "Shrek" were so good, so sophisticated, that they were scaring their intended audience. Why? The princess had fallen into what's known as the uncanny valley.
Mr. WESCHLER: Which was this notion by a Japanese roboticist named Masahiro Mori. The notion was that if you made a robot that was 50 percent lifelike, that was fantastic. If you made a robot that was 90 percent lifelike, that was fantastic. If you made it 95 percent lifelike, that was the best - oh, that was so great. If you made it 96 percent lifelike, it was a disaster. And the reason, essentially, is because a 95 percent lifelike robot is a robot that's incredibly lifelike. A 96 percent lifelike robot is a human being with something wrong.
YORK: Mori called it the uncanny valley, a play on Sigmund Freud's idea of the uncanny, something familiar and yet foreign at the same time. The makers of "Shrek," having learned their lesson, re-imagined Princess Fiona as a slightly more cartoony-looking love interest, thus avoiding the valley.
But "Final Fantasy," a $135 million digital adventure, which opened the same year as "Shrek," was fully animated with characters that were realistic in an unprecedented way and yet not real enough. Audiences reported feeling unsettled and the film bombed. The studio that made it later folded. On the other hand, "Avatar..."
(Soundbite of movie, "Avatar")
Mr. SAM WORTHINGTON (Actor): (As Jake Sully) Me and Norm are here to drive these remotely control bodies called Avatars. And they're grown from human DNA mixed with the DNA of the natives.
YORK: Avoids the uncanny valley because the aliens are distinctly alien - blue, stretched and unreal. The faces of the Na'vi don't trigger our uncanny reflexes because they're simply not human. Faces, despite 10 years of refinement in computer rendering, animators still can't accurately create them. So many muscles attached to each other moving in tandem, so many complex and inimitable plays of light.
Mr. WESCHLER: With faces and especially with the whites of eyes, light behaves in a quantum fashion, exactly the way it does in milk. So that if you want to create a digital glass of milk and have a digital light go around it, unless you use quantum physics, you're going to end up with something that looks like chalk.
YORK: And it's no coincidence that the digital movie company Pixar built its fortunes on protagonists that are easy to light. Shiny toys, cars, bugs, monsters, robots and old men with square heads who love balloons.
(Soundbite of movie, "Up")
Mr. JORDAN NAGAI (Actor): (As Russell) Are you in need of any assistance today, sir?
Mr. EDWARD ASNER (Actor): (As Carl Fredricksen) No.
Mr. NAGAI: Well, I got to help you across something.
Mr. ASNER: No, I'm doing fine.
(Soundbite of door slam)
YORK: But while it's clear that the uncanny valley alarms audiences, and Pixar's made a mint by sidestepping the problem, the question remains: What makes us feel this way and why? Karl MacDorman is professor of Computer Human Interaction at the Indiana University Department of Informatics. Intent on understanding the valley, he's been testing precisely what we feel when we look at near humans on the screen.
Professor KARL MACDORMAN (Computer Human Interaction, Department of Informatics, Indiana University): Out of perhaps, you know, 28 different emotions, there are about five key emotions that are highly predictive. And the most important one is fear and anxiety, disgust and shock. Fear stood out as being the most predictive of uncanny reaction.
YORK: There are a number of theories as to why we're afraid when we gaze at nearly real faces. One suggestion is that it's existential because we see the potential for being replaced by nearly-perfect computers. Theologians argue that we're seeing human imitators that lack a soul. But the most convincing explanation for the fear may be evolutionary. We see in uncanny faces something unhealthy or unappealing and our instinct is to recoil. Maybe they're contagious. Maybe they're not suitable mates.
Asif Ghazanfar is a professor in the Neuroscience Institute in the psychology department at Princeton University. He'd heard of the dread engendered by the uncanny valley. So, he sought to test the reaction with his evolutionary indicator of choice: Macaque monkeys.
(Soundbite of monkeys)
YORK: Ghazanfar created for his subjects three different kinds of what he calls synthetic monkey faces: one unrealistic, one realistic and one real. He flashed those faces on a screen for his five monkey subjects to watch in random order for two seconds each, and he tracked where their eyes went.
Professor ASIF GHAZANFAR (Neuroscience Institute, Princeton University): I mean, there's good reasons to think that they increased their looking times to things that they prefer. All five monkeys it was actually really remarkable -all five monkeys showed exactly the same pattern. When they look at the realistic, the one that we predict would elicit the uncanny valley response, they looked at those images the least amount of time, which also seems consistent with the interpretation that we're actually seeing a real uncanny valley effect.
YORK: Ghazanfar's research seems to suggest that the valley is real and the response is evolutionary, but we still don't know why.
Mr. WESCHLER: Sartre has this beautiful essay called "The Face." He writes: If I watch his eyes, I see that they are not fastened in his head, serene-like agate marbles. They are being created at each moment by what they look at.
YORK: Lawrence Weschler.
Mr. WESCHLER: It's a great notion, the notion that what we face when we face a face is the future in some sense. It's omnivorous with intent and with expectation and with desire and with fear in a way that a thigh is not, which is why animating it becomes so much more complicated and so much more exciting.
YORK: Scientist Asif Ghazanfar of Princeton envisions the creation of a digital human face that could help treat autism. And Karl MacDorman at Indiana University foresees a day when robots could alleviate loneliness in the elderly. But those real world visions of what could be accomplished when we cross the uncanny valley and can build a foolproof human likeness will raise new existential questions that Hollywood simply can't prepare us for.
MacDorman fears the day an elderly woman realizes that her beloved companion that keeps her company is not real. That's an uncanny shutter of a different kind, the kind we have when we stare in the face of what it means to be human.
NORRIS: That was On The Media producer Jamie York. You can hear a longer version of Jamie's story when it airs this weekend on WNYC's On The Media, or you can go to onthemedia.org.
NPR transcripts are created on a rush deadline by Verb8tm, Inc., an NPR contractor, and produced using a proprietary transcription process developed with NPR. This text may not be in its final form and may be updated or revised in the future. Accuracy and availability may vary. The authoritative record of NPR’s programming is the audio record.