Alibaba wants you to compare its new AI video generator to OpenAI's Sora. Otherwise, why use it to make Sora's most famous creation belt out a Dua Lipa song?
On Tuesday, an organization called the "Institute for Intelligent Computing" within the Chinese e-commerce juggernaut Alibaba released a paper about an intriguing new AI video generator it has developed that's shockingly good at turning still images of faces into passable actors and charismatic singers. The system is called EMO, a fun backronym supposedly drawn from the words "Emotive Portrait Alive" (though, in that case, why is it not called "EPO"?).
EMO is a peek into a future where a system like Sora makes video worlds, and rather than being populated by attractive mute people just kinda looking at each other, the "actors" in these AI creations say stuff — or even sing.
Alibaba put demo videos on GitHub to show off its new video-generating framework. These include a video of the Sora lady — famous for walking around AI-generated Tokyo just after a rainstorm — singing "Don't Start Now" by Dua Lipa and getting pretty funky with it.
The demos also reveal how EMO can, to cite one example, make Audrey Hepburn speak the audio from a viral clip of Riverdale's Lili Reinhart talking about how much she loves crying. In that clip, Hepburn's head maintains a rather soldier-like upright position, but her whole face — not just her mouth — really does seem to emote the words in the audio.
SEE ALSO:What was Sora trained on? Creatives demand answers.In contrast to this uncanny version of Hepburn, Reinhart in the original clip moves her head a whole lot, and she also emotes quite differently, so EMO doesn't seem to be a riff on the sort of AI face-swapping that went viral back in the mid-2010s and led to the rise of deepfakes in 2017.
Over the past few years, applications designed to generate facial animation from audio have cropped up, but they haven't been all that inspiring. For instance, the NVIDIA Omniverse software package touts an app with an audio-to-facial-animation framework called "Audio2Face" — which relies on 3D animation for its outputs rather than simply generating photorealistic video like EMO.
Despite Audio2Face only being two years old, the EMO demo makes it look like an antique. In a video that purports to show off its ability to mimic emotions while talking, the 3D face it depicts looks more like a puppet in a facial expression mask, while EMO's characters seem to express the shades of complex emotion that come across in each audio clip.
It's worth noting at this point that, like with Sora, we're assessing this AI framework based on a demo provided by its creators, and we don't actually have our hands on a usable version that we can test. So it's tough to imagine that right out of the gate this piece of software can churn out such convincingly human facial performances based on audio without significant trial and error, or task-specific fine-tuning.
The characters in the demos mostly aren't expressing speech that calls for extreme emotions — faces screwed up in rage, or melting down in tears, for instance — so it remains to be seen how EMO would handle heavy emotion with audio alone as its guide. What's more, despite being made in China, it's depicted as a total polyglot, capable of picking up on the phonics of English and Korean, and making the faces form the appropriate phonemes with decent — though far from perfect — fidelity. So in other words, it would be nice to see what would happen if you put audio of a very angry person speaking a lesser-known language into EMO to see how well it performed.
Also fascinating are the little embellishments between phrases — pursed lips or a downward glance — that insert emotion into the pauses rather than just the times when the lips are moving. These are examples of how a real human face emotes, and it's tantalizing to see EMO get them so right, even in such a limited demo.
According to the paper, EMO's model relies on a large dataset of audio and video (once again: from where?) to give it the reference points necessary to emote so realistically. And its diffusion-based approach apparently doesn't involve an intermediate step in which 3D models do part of the work. A reference-attention mechanismand a separate audio-attention mechanismare paired by EMO's model to provide animated characters whose facial animations match what comes across in the audio while remaining true to the facial characteristics of the provided base image.
It's an impressive collection of demos, and after watching them it's impossible not to imagine what's coming next. But if you make your money as an actor, try not to imagine too hard, because things get pretty disturbing pretty quick.
TopicsArtificial Intelligence
(责任编辑：時尚)
Despite IOC ban, Rio crowds get their political messages across
Billy Bush caught on tape having lewd conversation with Donald Trump
British man live
'Simpsons' creator: Donald Trump candidacy has gone 'beyond satire'PlayStation Now game streaming is coming to PCHere's George Takei chilling in zero gravity for the 'Star Trek' anniversary
There's nothing like good friends, good memories and zero gravity to celebrate a milestone. 。In honor
...[详细]Ivanka Trump puzzles everyone by unexpectedly liking this tweet
UPDATE: Oct. 10, 2016, 3:09 p.m. EDT Updated with a comment from a source close to Ivanka Trump's co
...[详细]Donald Trump is bad at 'Overwatch,' according to a billboard in Florida
UPDATE: Oct. 14, 2016, 3 p.m. EDT Mashablespoke to the group behind the billboard, learning why they
...[详细]LeBron James trashes Trump's 'locker room talk' while Tom Brady walks away
According to LeBron James, Donald Trump has a very poor understanding of what athletes actually talk
...[详细]One thing's for sure: you're never too old to learn. 。Massachusetts woman Clare Picciuto turned 100 F
...[详细]29 times Maisie Williams was the undisputed queen of social media
LONDON -- A girl may have no name, but she sure has a hell of a strong game on Instagram.When she's
...[详细]
There is a list — a short list — of San Francisco Giants postseason legends.This particu
...[详细]One tweet summarizes tonight's presidential debate
If you couldn't sit through 90 minutes of awkward pacing and arguing Sunday night, you can just read
...[详细]Nate Parker is finally thinking about the woman who accused him of rape
Nate Parker is getting a crash course in male privilege after, in his own words, not thinking about
...[详细]One man was charged $40 to hold his newborn baby
Can you imagine having to pay money to hold your own baby?That's pretty much what happened to Ryan G
...[详细]