NVIDIA announced DLSS (short for Deep Learning Super Sampling) back in 2018 as a new video rendering technique. With each iteration, DLSS has evolved, and NVIDIA envisions that DLSS 10 in the future could handle every aspect of rendering using AI.
In a recent AI Visuals' roundtable hosted by Digital Foundry, NVIDIA's VP of Applied Deep Learning Research, Bryan Catanzaro, was asked about his thoughts on the future of DLSS and the problem areas that machine learning could address. In response, he stated:
I do not believe that AI is gonna build games in a way where you just write a paragraph about making a cyberpunk game and then pop comes out something as good as Cyberpunk 2077. I do think that let's say DLSS 10 in the far future is going to be a completely neural rendering system that interfaces with a game engine in different ways, and because of that, it's going to be more immersive and more beautiful.
He mentioned a past demo of a world that was rendered 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 being rendered by a neural network, like, completely but it 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 an input to a neural network that would do all the rendering, so it was responsible basically for every part of the rendering process. Just getting that thing to run in real-time in 2018 was kind of a visionary thing.
Catanzaro said the image quality of the rendered game wasn't anything close to Cyberpunk 2077, but he thinks “long term this is where the graphics industry is going to be headed.”
We're going to be using generative AI more and more for the graphics process. Again, the reason for that is going to be the same as it is for every other application of AI, we're able to learn much more complicated functions by looking at huge data sets than we can by manually constructing algorithms bottom up.
While NVIDIA’s vision for future DLSS versions is enticing, we are far away from it being a reality. For now, you are left with DLSS 3.5, which was introduced last week. It brings what the company calls Ray Construction, a supercomputer AI-based method for improving ray-traced images in games, in contrast to the current method of using hand-tuned denoisers.