Now I will admit that if you don't compare them, the final image looks ok. Like if I did not know what was happening I likely wouldn't give it a second thought. It looks off but so many video games already look off that I don't think I would have really thought anything other than "well it's a video game".
But when compared to the original image it is so obvious that the artistry and the original intent is just completely lost.
They claim that the developers and artists have more control over this, well maybe if that is actually true (because we all know guardrails on AI have been perfect so far...) they should have been involved in using that control for the video showing this off. Otherwise I honestly hope this never ships.
But even if it does, the power requirements for this make it kinda DOA anyways.
But I'm also skeptical about whether they can pull this off in a way that doesn't exacerbate the already-severe issues DLSS has with latency and temporal stability. Enhancements that make for great screenshots often don't translate to great realtime gameplay.
A frame of the character shown 20 hours into the game doesn’t remember the random generated sexy face it gave that character 1 hour into the game.
Everything about this is so stupid.
Personally, think it's just people freaked out that it's being improved on by AI, and therefore apart of the "AI slop" trend. Think if they had done this all with no AI and just polygons, it'd be hailed as a large step forward in graphics.
... and btw, am just as freaked out about AI taking over the creative fields as a lot of others (am a musician myself), but have to try to objective, and in my opinion, DLSS 5 is impressive.
I do think this will eventually be a major part of the graphics pipeline, but I hope it will be limited and masked to things like hair, which is almost impossible to get right in real-time rendering.
I am really not a fan of this. Artificially changing graphics to make them 'look better' is similar to my feelings around the (awful) Halo Anniversary remaster.
Summed up nicely by Noodle - https://youtu.be/MyeCb99cb2Q (starts from 2:28)
same take as every other comment
That is not controversial at all. Everybody is mocking it.
As an aside, I'm starting to wonder if they are modifying engine settings when switching it on and off. There's clearly some amount of accumulation it has to do and its impossible to frame-by-frame a video of a monitor, but in [1] the first frame snaps from a dynamic shadow of the steeple to a generic small blob shadow, then gets entirely eliminated on the next frame.
[1] https://youtu.be/4ZlwTtgbgVA?t=435, [2] https://youtu.be/4ZlwTtgbgVA?t=326, [3] Cyberpunk hyper-realism mod: https://www.youtube.com/watch?v=_toA8lErAHg
Yeah, may be the fact that they are lighted differently from the original is turning people off. Understandable. For me, still find it impressive, and think the level detail in the faces and clothing is a full step up in capability.
That was essentially just Jensen Huang lying during his Q&A. DLSS5 uses the same input data as DLSS<5, which is just screen space color data and motion vectors. From NVIDIAs announcement: "DLSS 5 takes a game’s color and motion vectors for each frame as input, and uses an AI model to infuse the scene with photoreal lighting and materials that are anchored to source 3D content and consistent from frame to frame."
I agree, every shot has something to like, especially in fine details, but I question the feasibility of fixing the issues while running the model on a consumer GPU in realtime. Getting similar improvements without falling back to diffuse lighting would require the model to infer a huge amount of information about off-screen light sources and objects. I'm much more excited about putting my tensor cores and vram towards neural textures since they can actually add detail at the geometry level.
https://www.nvidia.com/en-us/geforce/news/dlss5-breakthrough...