At a press Q&A with Tom’s Hardware at GTC 2026, Nvidia CEO Jensen Huang downplayed criticism of DLSS 5, the corporate’s new use of AI and neural rendering to deduce how sure options of video games would look in the event that they had been extra photorealistic.
Go deeper with TH Premium: GPUs
“Well, first of all, they’re completely wrong,” Huang mentioned in response to a query from Tom’s Hardware editor-in-chief Paul Alcorn in regards to the criticism.
“The reason for that is because, as I have explained very carefully, DLSS 5 fuses controllability of the of geometry and textures and everything about the game with generative AI,” Huang continued.
He added that builders can nonetheless “fine-tune the generative AI” to make it match their fashion, including that DLSS 5 provides generative functionality to the present geometry of the sport, however that it “doesn’t change the artistic control.”
“It’s not post-processing, it’s not post-processing at the frame level, it’s generative control at the geometry level,” he mentioned.
Article continues beneath
Huang additionally mentioned that builders can strive the device and see how they need to use it, suggesting that it is as much as a developer to attempt to make a “toon shader” or see if the sport needs to be “made of glass.”
“All of that is in the control — direct control — of the game developer,” he mentioned. This could be very completely different than generative AI; it’s content-control generative AI. That’s why we name it neural rendering.”
We’ll see if the vocal players who say they dislike what they see change their thoughts as we see extra. DLSS 5 is about to launch within the fall, and there’ll doubtless be much more demos of this expertise which can be extra totally baked earlier than then.
Follow Tom’s Hardware on Google News, or add us as a preferred source, to get our newest information, evaluation, & opinions in your feeds.