The recently unveiled DLSS 5 from NVIDIA is currently seeing one of the most negative receptions in the industry in years, despite CEO Jensen Huang downplaying the overall criticism significantly in this year’s GTC event. After the initial critical reactions from both gamers and industry veterans alike, Huang stated that “Well, first of all, they’re completely wrong.”
“The reason for that is because, as I have explained very carefully, DLSS 5 fuses the controllability of geometry and textures and everything about the game with generative AI,” he continued.
According to the NVIDIA CEO, developers have complete control over the new tech and can fine tune how it’s going to end up looking on the finished product: “it’s not post-processing, it’s not post-processing at the frame level, it’s generative control at the geometry level,” Huang stated.
“All of that is in the control, direct control, of the game developer,” he said. This is very different than generative AI; it’s content-control generative AI. That’s why we call it neural rendering.”
But now, it turns out that even the game developers including art teams of both Ubisoft and Capcom, aren’t particularly enthusiastic about DLSS 5. Animator Mike York, who has previously worked on titles such as Death Stranding 2, has pointed out in a reaction video that the new upscaler is basically re-rendering the game and altering the intended design choices in a number of ways.
“The geometry isn’t being changed, but what’s happening is that it’s getting painted over, sort of. Every single frame is being painted over, it’s actually not showing the real geometry anymore,” York said.
And perhaps the most worrying element of DLSS 5 is that it’s in the process of removing one of the most uniquely human elements from videogame graphics which is the art direction and replacing it with generic looking visuals that looks like a heavily altered version of the original game.
