Nvidia recently announced its deep-learning super-sampling (DLSS) 5 technology, which is all set for launch in the fall. After witnessing the newly released teaser, gamers believe that the company might have crossed a line from mere upscaling into lighting and texture overhauls heavily influenced by “generative AI.”
Initially, DLSS was launched on RTX 2080 cards in 2018. Ars Technica reported that the result from DLSS 5 appears to be a "bland, uncanny gloss," receiving negative reactions from a large number of gamers.
Nvidia has called DLSS 5 “a real-time neural rendering model” to “deliver a new level of photoreal computer graphics previously only achieved in Hollywood visual effects.” In order to smooth out gaps, the earlier DLSS releases rendered upscaled frames or even created entirely new ones.
Nvidia CEO Jensen Huang said the latest technology melds “generative AI” with “handcrafted rendering”. This has been done for a “dramatic leap in visual realism while preserving the control artists need for creative expression.”
According to the company, the present generative video models are “difficult to precisely control and often lack predictability”.
On the other hand, DLSS 5 utilises the internal colour and motion vectors of a game to "infuse the scene with photoreal lighting and materials that are anchored to source 3D content and consistent from frame to frame.”
Also Read: Nvidia Makes Trillion-Dollar Forecast At Annual Product Expo
This data helps the system to “understand complex scene semantics such as characters, hair, fabric and translucent skin, along with environmental lighting conditions like front-lit, back-lit or overcast,” it added.
However, critics have said that DLSS 5 turns in-game faces into overly detailed versions of the original models. A few game developers have even highlighted the “artistic intent” angle.
Thomas Was Alone developer Mike Bithell said the new technology seems designed “for when you absolutely, positively, don't want any art direction in your gaming experience.”
Additionally, Gunfire Games Senior Concept Artist Jeff Talbot suggested that “in every shot the art direction was taken away for the senseless addition of ‘details.' Each DLSS 5 shot looked worse and had less character than the original. This is just a garbage AI Filter.”
Further, New Blood Interactive founder and CEO Dave Oshry said DLSS 5's “AI dogshit is actually depressing”.
Also Read: Nvidia Sees Sales Goal Topping $1 Trillion With New Markets
Speaking with Tom's Hardware at GTC 2026, Huang downplayed criticism of DLSS 5. "Well, first of all, they're completely wrong... 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".
Essential Business Intelligence, Continuous LIVE TV, Sharp Market Insights, Practical Personal Finance Advice and Latest Stories — On NDTV Profit.
