The Vergecast · Tuesday, September 22, 2026
Nvidia is pushing a new approach to rendering called "neural rendering," where low-fidelity scenes are used with AI to extrapolate and add elements. This strategy comes as Nvidia believes Moore's Law is dead. The company sees this as the future of rendering, potentially benefiting developers and gamers by reducing the computational load required for photorealistic graphics.
“Yeah, well DLSS in the past meant we've got this lower resolution that we're rendering at internally. And then we're using, you know, some form of of machine learning to take that and extrapolate, you know, kind of like way back in the day when you would have like a a low resolution image that you'd kind of try to stretch out and then, you know, sharpen it and and fill in the missing information. It was like that but powered by machine learning. So towards the end of it with DLSS 4.5, actually, getting pretty good.”
“DLSS 5 takes that and instead of just, you know, adding pixels that weren't there, it seems to be adding elements of the scene that weren't there or adding colors that weren't there. And Nvidia has strongly hinted. Not just hinted. They have said outright that this is where they believe the future of rendering is going. Because they just basically have been saying that Moore's Law where we can just have more and more transistors and bigger and bigger chips that can traditionally render better and better every year is completely dead. That's that Nvidia is kind of stands on that. And this concept of neural rendering is the future.”
“Where we take a low fidelity scene and then we use our best guesses based on a a trained AI model as to what exactly the intent was to have there.”