The world of Artificial Intelligences and technological development are increasingly surprising us. In this case we will talk about the future of DLSS 10which even predicts the end of graphics cards.
It is something quite surprising that we do not conceive today, but many experts are sure of all this. Let’s comment on it, see what you think.
DLSS 10, the future?
It all comes as a result of an interview with the vice president of research on applied deep learning, Bryan Catanzaro, who would be part of the NVIDIA team, a company characterized this last year by everything that has to do with AI and the future.
He himself assures that DLSS 10 “It will be a 100% neural rendering system” capable of replacing even graphics cards, interacting directly with the game, without needing your help.
AIs have shown us that they are capable of generating images that do not exist, enlarging one that we give them and doing anything we ask of them, which is why both Bryan Catanzaro and many of his team believe that Intelligence itself will create and render real-time images of any video game.
We can see an example with a demo in 2018 that shows us a world created solely with a neural network:
In 2018in the conference NeurIPSwe put together a really cool demo of a world that was being rendered by a neural network, in its entirety and completeness, but was being driven by a game engine.
So basically what we were doing was using the game engine to generate information about where things are and then using that as input to a neural network that would do all the rendering, so it was responsible for basically every part of the rendering process. rendering.
Making that work in real time in 2018 It was something visionary. The image quality we got certainly didn’t come close to Cyberpunk 2077, but I think in the long term it’s where the graphics industry will be headed. We will increasingly use generative AI for graphics processing.
In the current statements he tells us the following:
I think we’re going to have greater realism and hopefully also make it cheaper to create awesome AAA environments by moving to much, much more neural rendering. I think it will be a gradual process. The thing about traditional 3D Pipeline and game engines is that it’s controllable: you can have teams of artists build things and they have coherent stories, locations, everything. In fact, you can build a world with these tools.
Surely we are going to need those tools. I don’t think AI is going to create games in a way where you just write a paragraph about how to make a Cyberpunk-type game and then something as good as Cyberpunk 2077 comes out. I do think that, say, DLSS 10 in the distant future will be a fully neural rendering system that will interact with a game engine in different ways and, therefore, will be more immersive and more beautiful.
In short, not only will it create better graphics with fewer resources, but it will lower costs, increase the pace of video game production, and much more.
AI is just beginning, and our brain is not able to process how far it will go, but they assure us that it is closer than we think.