HomeGame GuidesNVIDIA sees DLSS 10 as a full neural rendering system with an...

NVIDIA sees DLSS 10 as a full neural rendering system with an interface to game engines

Published on

[ad_1]

Nvidia logo in black and green

NVIDIA announced DLSS (short for Deep Learning Super Sampling) More in 2018 as a new video processing technique. With each iteration, DLSS has evolved, and NVIDIA predicts that the future DLSS 10 will be able to handle every aspect of rendering using AI.

Recently The AI ​​Visuals Roundtable hosted by Digital FoundryNVIDIA’s VP of Applied Research for Deep Learning, Brian Catanzaro, was asked about his thoughts on the future of DLSS and the problem areas that machine learning can tackle. In response, he said:

I don’t believe AI is going to build games in a way where you just write a paragraph about making a cyberpunk game and then pop something good like Cyberpunk 2077. I do think we’ll assume that DLSS 10 in the far future is going to be a fully neural rendering system that interfaces with a game engine in various ways , and that’s why it will be more immersive and beautiful.

He mentioned a past demonstration of A A world worked by a neural network and driven by a game engine.

Back in 2018 at the NeurIPS conference, we actually put together a really cool demo of a world that was worked by a neural network, like, completely but it was driven by a game engine.

So, basically what we did was use the game engine to generate information about where things were and then use that as input to a neural network that would do all the processing, so it was basically responsible for every part of the processing process. . Just making this thing work in real time in 2018 was kind of a visionary thing.

Catanzaro said the image quality of the rendered game was nowhere near anything Cyberpunk 2077But he thinks that “in the long term this is where the graphics industry is headed.”

We are going to use more and more generative AI for the graphics process. Again, the reason for this will be the same as any other application of AI, we are able to learn much more complicated functions by looking at huge datasets than we can by manually building algorithms from the bottom up.

While NVIDIA’s vision of future DLSS versions is enticing, we are far from reality. For now, you’re stuck with DLSS 3.5, which was Introduced last week. It brings what the company calls Ray Construction, a supercomputer AI-based method to improve ray tracing images in games, as opposed to the current method of using hand-tuned denoisers.

(Through wccftech)



[ad_2]

Latest articles

More like this