This Person Does Not Exist

#1
https://www.thispersondoesnotexist.com/

It's a computer program created by geeks at Nvidia that creates hyper-realistic photographic quality faces of nonexistent people using a technology called 'Generative Adversarial Networks'.

Click refresh/reload, and you will get another nonexistent person.

https://interestingengineering.com/this-...the-future

Technical details here:

https://arxiv.org/pdf/1812.04948.pdf

Apparently it has two AI components: a generator and a discriminator. The generator generates images (at first crude) using an initial set of preprogrammed principles and the discriminator decides if the image is real or fake, based on comparing the generator's images with real life images according to its own innate set of principles. But it doesn't stop there, since the generator and the discriminator are neural network AIs that can learn, gradually getting better and better at their tasks as they compete with each other. In effect, each network is training the other network in kind of a circular loop. The goal is to generate better and better images that become so good that the discriminator eventually can't tell the difference between a real image and a fake one.

Apparently they've succeeded very spectacularly. At least human discriminators can't tell.

Considering that humans are primed by evolution to perceive faces, making us very good discriminators of faces (remember the uncanny valley) it's going to be very hard to trick a human with a fake image, making it a good test of the technology.

The technology doesn't just work with faces, it works with any sort of image. The scientific paper includes sets of computer generated fake images of cars, cats and room decors.

They are talking about developing the Generative Adversarial Network process to produce exceedingly lifelike virtual environments for various applications like video games.
Reply
#2
(Feb 16, 2019 10:22 PM)Yazata Wrote: The technology doesn't just work with faces, it works with any sort of image. The scientific paper includes sets of computer generated fake images of cars, cats and room decors.They are talking about developing the Generative Adversarial Network process to produce exceedingly lifelike virtual environments for various applications like video games.


Given that range, will probably put a lot of film actors out of work once further developments like whole body generation and animation are added. Realistic CGI of a whole new level. Never have to worry about child celebrities of that ilk growing up or the sexy stars getting too elderly for protagonist roles. Voice simulation is approaching new heights as well, so real people might not even be hired to supply that for the characters in the ultra-authentic "cartoon" cinema of the future.

And with creative speed like that, maybe the first step in computational solipsism. Being able generate a coherent external environment on the fly without having to maintain an entire virtual reality in storage (even when most of it is not immediately displayed on the screen POV of the observer). Essentially getting around to finally imitating what the dreaming apparatus of the brain does, only far more managed by regulated principles than dreams.

###
Reply
#3
With further advancement of BCI (Brain Computer Interfacing), such imagery could be used to manifest "dreams" with fictitious imagery perhaps a MAIA project.. Muse Artificial Intelligence Algorithm, which could support working out problems while asleep amongst other things.
Reply




Users browsing this thread: 1 Guest(s)