I thought DLSS tried to retain the original look to make it look better at lower resolutions as opposed to changing the visuals like it is being run through a “beauty” filter.
if I understand right, DLSS (outside frame generation, a relatively newer DLSS feature) isn’t interpolating frames, it’s upscaling frames. and its never before altered the look beyond just upscaling it.
this new shit is definitely a different direction for DLSS and it sucks and I hate it
You can write a shader that drastically alters the artwork too, and DLSS is basically a closed source ML shader running on a separate chip (come at me gamedevs 😤)
edit: tho don’t get me wrong it does suck. I don’t know why would I ever want a face filter in a video game
I don’t know why would I ever want a face filter in a video game
Actually I can see that being amazing as like a joke mod option. Imagine playing like Fallout or something and you can flip a toggle to make everyone look like handsome Squidward 😂
There has been machine learning for decades, but you’re right in that interpolating frames is quite different from the way generative AI works. Both DLSS versions rely on a form of neural network but the latest ones are diffusion models which are more controversial, for reasons I’m sure you know.
To be fair, DLSS (aka Deep Learning Super Sampling) was an ML filter from the start.
I’m all for dunking on it cause it sucks, but the AI bit is basically in the name.
I thought DLSS tried to retain the original look to make it look better at lower resolutions as opposed to changing the visuals like it is being run through a “beauty” filter.
Wasn’t it supposed to interpolate frames, not alter the whole look of the artwork? (I am ignorant of how DLSS works exactly)
Yes, but it has to make up details to do that because it gets a lower resolution image, or for frame gen it gets two frames it needs to interpolate
if I understand right, DLSS (outside frame generation, a relatively newer DLSS feature) isn’t interpolating frames, it’s upscaling frames. and its never before altered the look beyond just upscaling it.
this new shit is definitely a different direction for DLSS and it sucks and I hate it
You can write a shader that drastically alters the artwork too, and DLSS is basically a closed source ML shader running on a separate chip (come at me gamedevs 😤)
edit: tho don’t get me wrong it does suck. I don’t know why would I ever want a face filter in a video game
Actually I can see that being amazing as like a joke mod option. Imagine playing like Fallout or something and you can flip a toggle to make everyone look like handsome Squidward 😂
Now I want a fallout: new Vegas remaster but every ghoul is handsome Squidward…
I want Doom with a Teletubbies filter.
Because who doesn’t want uncanny semi-realistic faces on Bethesda’s abysmal facial animations?
There has been machine learning for decades, but you’re right in that interpolating frames is quite different from the way generative AI works. Both DLSS versions rely on a form of neural network but the latest ones are diffusion models which are more controversial, for reasons I’m sure you know.