NVIDIA announced DLSS 5: the breakthrough technology was criticized across the internet.

Yesterday, March 16, NVIDIA officially unveiled DLSS 5, a real-time neural rendering model that, according to the brand, “fills pixels with photorealistic lighting and materials.”

"Twenty-five years after NVIDIA invented the programmable shader, we're reinventing computer graphics. DLSS 5 combines hand-crafted rendering with generative AI to deliver a dramatic leap in visual realism while maintaining the control artists need for creative expression," said Jensen Huang, founder and CEO of NVIDIA.

The company explained that DLSS 5 takes in the game's color and dynamic vectors for each specific frame and then uses an AI model to fill the scene with photorealistic lighting and materials that are tied to the original 3D content and remain consistent from frame to frame. This next-generation technology operates in real time and supports resolutions up to 4K, guaranteeing a smooth and interactive gameplay experience. The company also claims that this technology will significantly improve the final image quality.

The AI ​​model powering DLSS 5 is trained end-to-end to understand complex scene semantics—characters, hair, cloth, skin, and ambient lighting conditions (frontal and backlighting, overcast conditions). All of this is accomplished by analyzing a single frame, and DLSS 5 then uses its deep knowledge to generate visually accurate images that enhance the scene's visuals while preserving the original structure and semantics. And this technology, according to NVIDIA, is already supported by the market's largest publishers and game developers, including Bethesda, CAPCOM, Hotta Studio, NetEase, NCSOFT, S-GAME, Tencent, Ubisoft, and Warner Bros. Games.

However, not all developers and gamers are happy with this innovation. Developers believe that NVIDIA is using its AI technologies to re-render their games, depriving creators of their unique style and the opportunity for self-expression. Meanwhile, gamers are calling DLSS 5 yet another "neuroslop," as the AI ​​generation, even in NVIDIA's own examples, looks terrible in places, meaning the reality will be even worse.

Source