By using this site, you agree to our Privacy Policy and our Terms of Use. Close
ConciousMan said:
ConsoleWarVet said:

I really dislike DLSS as a concept. TVs boasted something similar years back, and it made The Matrix look blue. All the fake frames that it generated didn’t have the right colour, so it gave the illusion of the real ones being blue as well.

DLSS may have improved on a technological level, but it still imposes itself upon the artistic intent of the developers when it creates its own frames.

It is censorship in real-time if we remember the AI simulated content instead of the game itself.

DLSS is an upscaling technique, not AI filter tech like neural rendering. The main purpose of AI upscaling like DLSS is to deliver correct looking images upscaled from lower resolution with anti aliasing applied to them. Neural rendering is a completely different technology using various coordinates, 3D data, vectors etc. to create an image through the use of machine learning and algorithms. So some people might not like neural rendering, but the majority will want to use upscaling, especially when performance is low. Now, the biggest misstep that Nvidia made IMO is to add neural rendering under DLSS tech stack. If they categorized NR under different name like Reflex or PhysX, then the negative feedback wouldn't be that profound.

DLSS also uses AI-generated frames.  It inserts those frames between genuinely rendered frames.  That is called DLSS AI Frame Generation and has been around since DLSS 3.

Further, the AI in DLSS Super Resolution (the process you described) independently fills in “missing details” as part of its up scaling process.

Both of these censor the artist’s work in real-time by imposing changes they never intended.  It also means you are playing a simulated version of the game instead of the actual game if the AI generates enough frames and alters them in the upscaling process.