Posted on 05/29/2019 6:30:02 AM PDT by BenLurkin
A video uploaded to YouTube last week by engineer Egor Zakharov shows the iconic portrait translated into three different video clips, each featuring Mona Lisa moving her mouth and turning her head as if in conversation — demonstrating that we can now produce realistic avatars using a single image.
Moscow-based Zakharov, an AI researcher with the Skolkovo Institute of Science and Technology and the Samsung AI Center, and his colleagues published their findings, which have not been peer-reviewed, in the journal arXiv.
Three-dimensional models of the human head are deeply complex, requiring “tens of millions of parameters,” the study authors say. Even with this advanced technology, passing living portraits off as the real deal isn’t likely as our eyes are very good at spotting “even minor mistakes” in digital portrayals of humans. Experts call this phenomenon the “uncanny valley effect,” denoting the unsettling feeling people experience when they see a digital human depiction that looks eerily close to reality.
Traditionally, these digital duplicates were made with a technique called generative adversarial network (GAN), wherein an AI simply attempts to forge a lifelike image. But Samsung’s new system instead scans for facial “landmarks,” reducing the image to just a nose, mouth, eyes, eyebrows and a chin, to produce a sequence of entirely novel facial expressions that seem to give the once-immutable images a personality.
(Excerpt) Read more at nypost.com ...
The day is coming when a video will be able to be produced that will be indistinguishable from the real thing.
This will not be a good thing, because nothing will be trusted.
Creepy.
She is saying...
“why don’t you ever pick up your socks and put them in the laundry basket?”
This is way too “UNCANNY VALLEY” for me.... Not lifelike at all... just CREEPY as all hell.
That’s pretty neat. I saw something where they took a WWI photo, colored it and made it come into action using a similar process. It really helps us remember that these were actual people.
As the old saying goes — “Nothing is true; everything is permitted.”
I think you’re wrong. When nobody is “Trusting” everyone will need to be convinced, not so easily fooled. Distrustful people are smarter and more likely to know the truth, seek the truth.
The point is, eventually the technology will get there.
What you say is borne out in the Bible:
Revelation13:15 And he had power to give life unto the image of the beast, that the image of the beast should both speak, and cause that as many as would not worship the image of the beast should be killed.
...those unholy Boston Dynamics dog creatures...
...the future is gonna be a scary place indeed...
Yes and no. Maybe it will force people to use logic, reason, and facts to draw conclusions and not just some knee jerk based on a 12 second video clip.
What next, the media distorting the news and lying to the people...
Great...now she won’t stop talking
They made her face thinner.
No, she won’t won’t. But look at the bright side. Her conversation is mostly about her.
The Internet, Web and attendant technologies have already created a situation where people are always ready to be suspicious.
looks like they used a “valley girl” as a model...I saw the Mona Lisa up close, in 1976, before they covered it, and barricaded it...wonder if they would put this video next to it, now...???
She reminds me of one of the secretaries at an previous workplace.
Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.