This was actually the sub-headline of the article but I thought was the more important party of the article.
Speaking with developers and artists at studios that have agreed to DLSS 5, including CAPCOM and Ubisoft, Insider Gaming was told that the DLSS 5 tech was revealed to them at the same time as everyone else.
“We found out at the same time as the public,” said one Ubisoft developer.
Developers at CAPCOM tell Insider Gaming that the announcement and the publisher’s involvement were particularly shocking, as CAPCOM has previously been historically very “anti-AI” with projects such as Resident Evil Requiem and other unannounced projects in development. Some at the publisher fear that the DLSS 5 announcement could prompt a change in the publisher’s view on generative AI and its implementation in its games.
That’s why only studio quality headphones are even worth listening to music on, if you’re not hearing exactly what was intended then it’s shit garbage. Too bad if you’re poor
Not sure what studio grade you are talking about, every single headphone has its own interpretation. Some “studio grade” headphones are so shrill to my ear that they are only good for detail work, some of them are pleasant enough for general listening. AKG K240 has been a standard for many years, and it sounds honey-glazed compared to some Beyerdynamics.
My Sony MDR-7506 are studio quality reference headphones, and they only cost me £80.
This is kinda kinda a bad example, it’s more akin to listening to a bad cover of the original song. Also this tech sure as shit isn’t going to run on cheap hardware which makes it even more egregious.
No, because the original information is still there, it’s just filtered on top. Exactly like how listening to the same audio on different headphones can sound completely different.
Edit: Because a dip/rise in a certain frequency can completely change the sound of any individual element of sound.
If you put new information on top of a pixel, the pixel is changed and it is no longer the original information. Your headphones example would be more accurately applied to the visual medium as running custom color profiles, like adjusting saturation and contrast. The original information is there (music waveform or pixel color) but affected by delivery (bass boost or colorblind adjustments).
I’m not sure I understand the difference when DLSS is a toggle.
You made exactly my point in your last sentence.
The DLSS 5 effect is less like a different pair of headphones that don’t have a flat response and more like if your music player added AI generated instruments to the songs in your music library. I think that was what the previous poster was arguing (I agree with them).
Part of me wonders if it is internally consistent, or if Leon’s face changes just a little every time he pops up in a new scene in the new RE with DLSS on.
But it’s details not entire extra characters, so it’s literally not “adding instruments” it’s attempting to sharpen details based on prior frames values for various parts of the image.
I guess it depends on how you want to interpret the analogy. It looked to me to be adding facial features, details in the background, and changing lighting from the videos and images I saw.
So maybe with your parameters for the analogy it’s more like if you went to listen to a Lo-Fi, basement recorded song using cheap gear and microphones, and your AI music player “sharpened details” to make it sound like it was recorded in higher detail by shaping the tracks and adding frames and increasing the bit rate while adding impulse responses and other emulated effects to make the recording sound more detailed/hi-fi.
For many people this would ruin the song, but I’m sure there are people out there who would love that sort of feature.
Exactly, thank you for understanding what I’m trying to say, and DLSS isn’t a required feature, it can easily be toggled.
mixing headphones aren’t expensive. industry standard headphones cost less than a lot of consumer grade headphones. don’t ask me to list examples but I’ll do it if you want
I mean I own a pair of sennheiser HD800, let’s compare audio quality.
But I’m obviously not saying it’s a good argument, I figured the sarcasm was evident, I think the “its not the original intention of the artist” argument is a bad one.
There are plenty of legitimate arguments against DLSS, such as companies not properly optimizing their games because they can just make it “good enough” and tell people to use DLSS. That is obviously bad.
Adjusting literally any of the many possible settings in a game “takes away from the original artistic vision” yet generally we see people complain if certain options to their taste/needs isn’t present.
Low quality headphones don’t add sounds that doesn’t exist in the original track. The thing with DLSS is that it adds details that doesn’t exist in the original image.
It sure does take away and distort sounds, to the extent where it can sound very very different.
Poor headphones takes something away, but (unless they’re so cheap they pick up static) it won’t add anything to the song. What Nvidia is selling, in terms of audio, is having an AI filter between the song and your headphones that enhances the sound however it sees fit. It might take something away but more often than not it’s just going to add something to it. You want to listen to Bad Bunny but the AI is going to generate English over Spanish because people are more likely to understand what he’s singing about if it’s in English. If you had headphones like that you’d throw them in the trash because they are trash.
That actually sounds really fucking cool, if you could automatically translate songs in real time? That would be bad because it’s not the original artistic version of the song? Are we really stooping to that level of groupthink where having options to change how you enjoy something is actually a bad thing now?
It takes away sounds, but don’t hallucinate new ones
Does that matter when all the arguments I’m seeing against it are “its not the original vision of the artist” as if most of the corporate garbage games had any soul to begin with?
The original vision is not the same, what can be changed are now all bad? I remember when people complained about games not having a way to disable bloom or chromatic abberation or whatever, that somehow wasn’t taking away from the “original artistic vision” but now we have to get out our pitchforks?
Imagine listening to a song you know, but the headphones keeps adding new instruments and sounds that doesn’t belong to it. It’s not consistent either. Every time you listen to the track it hallucinates new instruments. The artist were never part of these sounds.
That’s DLSS 5.
Adding insrruments would be more like if entire NPCs apear that weren’t there, it’s more like frequency expanding compressed/lossy audio.