Comment on Google is going ‘all in’ on AI. It’s part of a troubling trend in big tech
LainTrain@lemmy.dbzer0.com 3 days agoAnd it’s fucking awful.
People didn’t “want it” neither before nor after it was forced into being a thing, people had no choice because of GPU prices, especially console peasants stuck with their AMD APUs on par with like a GTX 1070 where a middleman built their PC for them under £600 + hundreds in PS Plus/game fees over years to come.
DLSS is even worse cancer than TAA, the washed out blurry slop only looks good on YouTube videos due to the compression. It’s one thing if you’re playing in the extremes of low performance and need a crutch, e.g. steam deck, it’s a whole other when you make your game look like dog shit then use fancy FXAA and motion blur to cover it up so you can’t see.
FreedomAdvocate@lemmy.net.au 3 days ago
DLSS? No way lol. DLSS often gives better image quality than native resolution, and gives you a choice in image quality vs performance increase options. It’s a god send.
You’ve clearly never used DLSS, at least not DLSS3 or 4. I’ve got a 4070 Super and Ryzen 7 and I use DLSS by choice literally every time it’s available.
pycorax@lemmy.world 3 days ago
It’s only better imo if you set it to native resolution for the AA. If you set it to anything below that, there’s definitely still artifacting. It’s not crazy obvious but no way it’s not noticeable, especially if you have a larger screen.
Venator@lemmy.nz 3 days ago
Results vary wildly depending on the game or situation, mainly depending on how fast the camera moves, and how cluttered or dark the environment is. It does pretty well in cyberpunk when you’re walking around the city on a sunny day with a low camera sensitivity, but looks pretty bad when driving in the rain at night.
FreedomAdvocate@lemmy.net.au 3 days ago
There might be some slight artifacting sometimes, but theres also significant improvements on sub-pixel detail compared to native that are far more noticeable.
I play on a 75" tv and at DLSS Quality profile you couldn’t tell it’s not native.
LainTrain@lemmy.dbzer0.com 3 days ago
Lolwut? No it doesn’t? Yeah it turns off TAA so it might look sharper at first, and if you turn off the ugly ass sharpening then it’s playable but literally any other option looks better than TAA, including TXAA from early 2010s lol.
Do you maybe mean DLAA? I Have an RTX 3090 and a 9800X3D. It’s ok. When the option exists I just crank up the res or turn on MSAA instead. Much better.
If you mean DLSS, my condolences. I’d rather play with FXAA most of the time.
The only game I’ll use DLSS (on Temporal+Quality) in is CP2077 with Path Tracing. With Ray Reconstruction it’s almost worth the blurriness, especially because that game forces TAA unless you use DLAA/DLSS and I don’t get the framerate. Maybe one day I’ll have the hardware needed to run it with PT and DLAA
FreedomAdvocate@lemmy.net.au 3 days ago
What are you talking about “temporal+quality” for DLSS? That’s not a thing.
DLSS I’m talking about. There are many comparisons out there showing how amazing it is, often resulting in better IQ than native.
LainTrain@lemmy.dbzer0.com 2 days ago
Sorry I was mistaken, it’s not “temporal”, I meant “transformer”, as in the “transformer model”, as here in CP2077.
Image
No, AI upscaling from a lower resolution will never be better than just running the game at the native resolution it’s being upscaled to. Most of the time it’s just blurry slop with sharpening applied.
Even if it was, any added detail is either literally just a sharpening post-processing filter akin to the added detail of a cheap Walmart “HD Ready” TV circa 2007 with sharpening cranked up, or outright fictional, and does not exist within the game files itself, and if by “better” we agree that it’s the most high fidelity representation of the game as it exists on disk, then AI cannot ever be better.
By it’s very nature, the ML model is just “guessing” what the frame might look like if it was rendered at native resolution. It’s not an accurate representation of the render output or artistic intent. Is it impressive? Yes of course, it’s a miracle of technology and a result of brilliant engineering and research in the ML field applied creatively and practically, but it does not result in a better image than native, nor does it aim to do so.
I mention FXAA because really the only reason we use “AI upscalers” is because anti-aliasing is really really computationally expensive.
The single most immediately evident and obvious consequence of a low render resolution is aliasing first and foremost. Almost all other aspects of a game’s graphics are usually completely detached from this like e.g. texture resolution.
The reason aliasing happens in the first place is because our ability to create, ship, process and render increasingly high polygon count games has massive surpassed our ability to push pixels on screen in real time.
Or course legibility suffers at lower resolution as well, but not nearly as much as smoothness of edges on high-polygon objects.
So for assets that would look really good at say, 4K, we run them at 720p instead, and this creates jagged edges because we literally cannot make the thing fit into the pixels we’re pushing.
The best and most direct solution will always be just to render the game at a much higher resolution. But that kills framerates.
We can’t do that, so we resort to Anti-Aliasing techniques instead. The most simple of which is MSAA which just multi-samples (renders at higher res) those edges and downscales them.
But it’s also very very expensive to do computationally. GPUs capable of doing it alongside other bells and whistles we have like Ray Tracing simply don’t exist, and if they did they’d cost too much, and even then, most games have to target consoles, which are solidly beat out by a flagship GPU even from several years ago.
One other solution is to blur these jagged edges out, sacrificing detail for a “smooth” look.
This is what FXAA does, but this creates a blurry image. This became very prevalent during the 7th Gen console era in particular because they simply couldn’t push more than 720p in most games, in an era where Full HD TVs had become fairly common towards the end and shiny, polished graphics in trailers became a major way to make sales, this was further worsened by the fact Motion Blur was often used to cover up low framerates and replicate the look of sleek modern (at the time) digital blockbusters.
SMAA fixed some of FXAA’s issues by being more selective about which pixels were blurred, and TAA eliminated the shimmering effect by also taking into account which pixels should be blurred across multiple frames.
Beyond this there are other tricks, like checkerboard rendering, where we render the frame in chunks at different resolutions based on what the player may or may not be looking at.
In VR we also use foveated rendering to render an FOV cone in front of the players immediate vision at a higher res than what would be in their periphery/outside the eye’s natural focus, with eye tracking tech, this actually works really well.
But none of these are very good solutions, so we resort to another ugly, but potentially less bad solution, solution, which is just rendering the game at a lower resolution and upscaling it, like a DVD played on an HDTV, but instead of a traditional upscaling algo like Lanczoz, we use DLSS, which reconstructs detail lost from a lower resolution render, based on context of the frame using machine learning, which is efficient because of tensor cores now included on every GPU making N-dimensional array multiplication and mixed precision FP math relatively computationally cheap.
DLSS often looks better compared to FXAA, SMAA and TAA because all of those just literally blur the image in different ways, without any detail reconstruction, but it is not comparable to any real anti-aliasing technique like MSAA.
But DLSS always renders at a lower res than native, so it will never be 1:1 a true native image, it’s just an upscale. That’s okay, because that’s not the point. The purpose of DLSS isn’t to boost quality, it’s to be a crutch for low performance, it’s why turning off even Quality presets for DLSS will often tank performance.
There is one situation where DLSS can look better than native, and it’s if you instead of typical applications of DLSS which downscales the image, then upscales it with ML guesswork, use it to upscale the image from native, to a higher target res instead and output that.
In Nvidia settings I believe this is called DL DSR factors.