Slashdot Mirror
Nvidia Uses AI To Render Virtual Worlds In Real Time (tomshardware.com)
Nvidia is using artificial intelligence to draw new worlds without using traditional modeling techniques or graphics rendering engines. "This new technology uses an AI deep neural network to analyze existing videos and then apply the visual elements to new 3D environments," reports Tom's Hardware. From the report: Nvidia claims this new technology could provide a revolutionary step forward in creating 3D worlds because the AI models are trained from video to automatically render buildings, trees, vehicles, and objects into new 3D worlds, instead of requiring the normal painstaking process of modeling the scene elements. But the project is still a work in progress. As we can see from [this image], which was generated in real time on a Nvidia Titan V graphics card using its Tensor cores, the rendered scene isn't as crisp as we would expect in real life, and it isn't as clear as we would expect with a normal modeled scene in a 3D environment. However, the result is much more impressive when we see the real-time output in [this YouTube video]. The key here is speed: The AI generates these scenes in real time.
It seems that this system needs lots of guided experience with the real world to accomplish its goals. How will we teach it to render big butt cheeks?
"oooh, aaahhh, wake me when it doesn't look like a shitty overlay of VHS video"
Whenever I see someone creating things like this it makes me realise how dumb I am in comparison! :-)
You folks dont exist until I go on slashdot... whos cat was that :)
[($)]
But is the AI punishing those in the virtual world who aren't helping bring about an AI that can simulate virtual worlds?
And where are the blockchain and cloud aspects from this announcement? A PR release without full line in buzzword bingo is not really worth reading.
Comment removed based on user account deletion
One step closer to The Matrix. Once Nvidia figures out how to interface their renders with the visual cortex, we can start putting humans into their pods. The Age of Bio-Electricity is nearly upon us!
Its like the deepfakes. Make a movie of anyone doing anything.
I don't see any rendering here. The static picture just shows an ugly colored copy of the original, nothing new. What have they created? real-time Photoshop filters?
Also, the Gangnam Style video is explained as "we used AI to synchronize the movements".
Impressive... not.
Real time.
For a 100 year old oak, it only needs a hundred years, real time.
Bullshit company. Bullshit products. Bullshit drivers.
upload my HODLgasms in realtime.
... is alive and well. Nick Bostrom wins the day.
. . . to do what algorithms have always been used for. Fixed this one, too. This is not news. It might as well say, 'Nvidia Uses Computers For Computing'. Millennials are just sad, man.
...was pretty damned impressive. Training sims will be a lot more effective anyway.
Social Media Handywoman at Texas Boys Balloo
Particular example, I haven't looked at. But the tech was announced with the 2080 line. It let's them realistically predict pixrls they don't have the time to compute, even when dealing with global illumination/multiple bounce's of photons
It sounds like they're just using the ai to generate texture maps. In the video they segment the real time video into discrete objects which they color differently. Then they feed that into the ai to get the final results. If I'm understanding that right then they're basically just using AI to generate a texture map which in of itself isn't trivial but still... not like the machines are on the verge of taking over.
If successful it would do little more rob people of a creative outlet and a living, for a lot of that stuff you saw in computer games was art, as well as bread-and-butter. What problem does it solve?
https://www.youtube.com/c/BrendaEM
Waiting for someone to comment "that's not AI", as always happens with any story about AI.