Shortly after NVIDIA released their next-gen upscaler DLSS 5 last week, gamers and developers alike have expressed their disdain in the new tech which fundamentally alters art direction in games in favor of producing a sharper and shinier image. And even though the FPS gains could be impressive, the modification of the artistic intent is what makes NVIDIA’s new upscaler go too far, for all the wrong reasons.
Even though CEO Jensen Huang has stated that all the parameters of DLSS 5 are ultimately in the hands of the developers to control and fine tune, but it’s still alarming how much alteration is clearly taking place which also makes the results look lifeless and generic.
And now the NVIDIA CEO has stated that personally he doesn’t favor “AI-slop” in gaming at all, in a recent episode of the Lex Fridmann podcast, he remarked on the current controversy surrounding DLSS 5: “I think their perspective makes sense. And I could see where they’re coming from, because I don’t like AI slop myself.”
“You know, all of the AI-generated content increasingly looks similar and they’re all beautiful, so I’m empathetic towards what they’re thinking,” he added.
However, according to Huang, that’s far from what DLSS 5 is, at least in it’s intention, as the new upscaler is “3D conditioned, 3D guided. It’s ground truth structure [is] data guided.” He also emphasized that the end result in DLSS 5 represents the “artistry of the artist” and it “enhances but does not change” the original 3D scenes in the game.
DLSS 5 won’t be arriving officially before fall this year, which gives more than enough time for NVIDIA to fine tune, adjust and even dial down on the ‘AI’ parts of the upscaler and just focus on the FPS gains instead, which is what the upscaling technologies are all about.
