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. Now although 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 taking place which also makes the results look lifeless and generic.
And now in a statement to Youtuber Danier Owen, Jacob Freeman from NVIDIA has clarified several points on the new DLSS 5 and states that the algorithm is indeed taking frames from the game and essentially drawing a new image on top of it.
“Yes, DLSS 5 takes a 2D frame plus motion vectors as input” and adding that: “DLSS 5 is trained end to end 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, all by analyzing a single frame.”
Which basically confirms that DLSS 5 alters the original design choices of developers to a degree, and that’s exactly what makes the new upscaler feel so out of place especially compared to it’s previous versions where the main aim was always about getting more FPS while making minimal compromises in visual fidelity.
In a nutshell, the highly divisive tech could take the entire industry to a place where art direction in visuals will have a lot less meaning than it does now which could also result in a lot of artists being let go by the studios and videogames losing a huge part of what makes their visuals look and feel unique.
