AMD has today revealed AMD FidelityFX Super Resolution 2.0, the next-generation version of their impressive spatial upscaling tech that can really help improve performance.
For those who don't use it and are confused: the whole idea is that it produces high-resolution outputs from lower resolution inputs. It's one way to get good performance at 4K for example, for games that are a bit too resource intensive. It can work with many resolutions and the Steam Deck has FSR built-in.
There's limitations of course, and AMD explained these examples for FSR 1.0:
- FSR 1.0 requires a high quality anti-aliased source image, which is not always available without making further changes to code and/or the engine.
- Upscaling quality is unavoidably a function of the source resolution input. So with a low resolution source, there is just not enough information with a spatial upscaler for thin detail.
Bring on FSR 2.0 then! Which continues to be open source.
"FSR 2.0 is the result of years of research from AMD, and is developed from the ground up. It uses cutting-edge temporal algorithms to reconstruct fine geometric and texture detail in the upscaled image, along with high-quality anti-aliasing."
Some of what's new in FSR 2.0 include:
- Delivers similar or better than native image quality using temporal data.
- Includes high-quality anti-aliasing.
- Higher image quality than FSR 1.0 at all quality presets/resolutions.
- Does not require dedicated Machine Learning (ML) hardware.
- Boosts framerates in supported games across a wide range of products and platforms, both AMD and select competitors.
It will continue to work across all vendors too so NVIDIA and Intel will also benefit from this. Since it's open source, any developer can just pick it up and use it.
FSR 2.0 temporal upscaling uses frame color, depth, and motion vectors in the rendering pipeline and leverages information from past frames to create very high-quality upscaled output and it also includes optimized high-quality anti-aliasing. Spatial upscaling solutions like FSR 1.0 use data from the current frame to create the upscaled output and rely on the separate anti-aliasing incorporated into a game’s rendering pipeline. Because of these differences, FidelityFX Super Resolution 2.0 delivers significantly higher image quality than FSR 1.0 at all quality mode presets and screen resolutions.
An example AMD included was DEATHLOOP which is adding support for it:
YouTube videos require cookies, you must accept their cookies to view. View cookie preferences.
Direct Link
Direct Link
When will it actually be available? They're not saying other than a vague "Q2 2022". They will be attending GDC though next week to give a talk on it.
Article taken from GamingOnLinux.com.
Some you may have missed, popular articles from the last month:
The comments on this article are closed.
Can't wait to try it, some games implement tragically bad AA.
2 Likes, Who?
soulsource Mar 17, 2022
The
on the announcement page made my day.
<meta name="description" content="Time. Get it? Never mind." />on the announcement page made my day.
3 Likes, Who?
Video compression technology meets real time rendering.
So cool to have this tech free for anyone to use. Hopefully Intel follows the same with XeSS and both techs kills the proprietary crap from the green side.
So cool to have this tech free for anyone to use. Hopefully Intel follows the same with XeSS and both techs kills the proprietary crap from the green side.
2 Likes, Who?
gradyvuckovic Mar 17, 2022
QuoteFSR 2.0 temporal upscaling uses frame color, depth, and motion vectors in the rendering pipeline
That doesn't sound promising for the chances of getting something like FSR 2.0 built into Steam OS.
FSR 1.0 was easy enough because it could just take a single frame image and scale it, but FSR 2.0 will need depth and motion vectors in addition to colour. I don't see how something like Gamescope could have access to that data.
1 Likes, Who?
Doc Angelo Mar 17, 2022
> Does not require dedicated Machine Learning (ML) hardware
The meaning of the terms around "artificial intelligence" are weird. There's no machine learning hardware on RTX cards as well. RTX cards simply execute the process that was the result of the machine learning that was done on different hardware - which also happened to be regular hardware.
The meaning of the terms around "artificial intelligence" are weird. There's no machine learning hardware on RTX cards as well. RTX cards simply execute the process that was the result of the machine learning that was done on different hardware - which also happened to be regular hardware.
1 Likes, Who?
Quoting: gradyvuckovicQuoteFSR 2.0 temporal upscaling uses frame color, depth, and motion vectors in the rendering pipeline
That doesn't sound promising for the chances of getting something like FSR 2.0 built into Steam OS.
FSR 1.0 was easy enough because it could just take a single frame image and scale it, but FSR 2.0 will need depth and motion vectors in addition to colour. I don't see how something like Gamescope could have access to that data.
Those "vectors" are most likely calculated from previous frames and not the vectors used in the game engine. So the data can be extracted by saving the image of previous frames.
Quoting: Doc Angelo> Does not require dedicated Machine Learning (ML) hardware
The meaning of the terms around "artificial intelligence" are weird. There's no machine learning hardware on RTX cards as well. RTX cards simply execute the process that was the result of the machine learning that was done on different hardware - which also happened to be regular hardware.
Actually there is. Machine learning requires a very limited and specific set of instructions. Nvidia does have hardware for this included in their GPU to speed things up. It is true that they use other computers to calculate the weights for the machine learning model, but without the dedicated part, even the creation of the model itself would probably have been to expensive.
2 Likes, Who?
mAdCraZyaJ Mar 17, 2022
If this continues to be supported on Vega hardware then I am very happy! Hopefully, it will work with Gamescope or Proton as well.
0 Likes
Doc Angelo Mar 17, 2022
Quoting: DonkeyActually there is. Machine learning requires a very limited and specific set of instructions. Nvidia does have hardware for this included in their GPU to speed things up. It is true that they use other computers to calculate the weights for the machine learning model, but without the dedicated part, even the creation of the model itself would probably have been to expensive.
I'm not sure what you're saying. As far as I know, there is no actual machine learning going on in the RTX cards. Just the execution of the models. Yes, they use hardware that is well fitted for that task, but it's just the execution, not the machine learning itself.
I'm not sure what you mean with "very limited and specific instructions" for ML. ML is possible on any hardware, as far as I know. Not efficient maybe, but possible. What kind of instructions are needed for ML in your view?
0 Likes
soulsource Mar 17, 2022
Quoting: DonkeyQuoting: gradyvuckovicQuoteFSR 2.0 temporal upscaling uses frame color, depth, and motion vectors in the rendering pipeline
That doesn't sound promising for the chances of getting something like FSR 2.0 built into Steam OS.
FSR 1.0 was easy enough because it could just take a single frame image and scale it, but FSR 2.0 will need depth and motion vectors in addition to colour. I don't see how something like Gamescope could have access to that data.
Those "vectors" are most likely calculated from previous frames and not the vectors used in the game engine. So the data can be extracted by saving the image of previous frames.
The diagram on the announcement page looks more like it's going to use the depth/motion buffers directly.
1 Likes, Who?
Does some neural antialiasing (not upscaling) solution exist in the wild?
0 Likes
Doc Angelo Mar 17, 2022
Quoting: axredneckDoes some neural antialiasing (not upscaling) solution exist in the wild?
In some way, FXAA and MLAA are like that. They analyze the already rendered image and change colors of pixels where the aliasing effect is visible.
0 Likes
somebody1121 Mar 17, 2022
I hope they release the source code soon so godot 4 can add this (Although it need some TAA implementation first for the motion vectors)
0 Likes
Quoting: Doc AngeloI mean more advanced techniques which not only remove ladders but try to reconstruct small details like wires.Quoting: axredneckDoes some neural antialiasing (not upscaling) solution exist in the wild?
In some way, FXAA and MLAA are like that. They analyze the already rendered image and change colors of pixels where the aliasing effect is visible.
Last edited by axredneck on 17 March 2022 at 6:06 pm UTC
0 Likes
Doc Angelo Mar 17, 2022
Quoting: axredneckI mean more advanced techniques which not only remove ladders but try to reconstruct small details like wires.
You mean wires that turn up as visually disconnected pixel strings? You MUST use the technologies in question for that, AMD FidelityFX or Nvidia DLSS. That's pretty much what they are intended for.
2 Likes, Who?
I'm curious to see how it will work with static frames.
I imagine that temporal AA induces some sort of subtle movement to the camera (?).
It this is true, then it would not be possible to implement such thing on compositor side, like with FSR today.
Somebody has some insight on TAA?
I imagine that temporal AA induces some sort of subtle movement to the camera (?).
It this is true, then it would not be possible to implement such thing on compositor side, like with FSR today.
Somebody has some insight on TAA?
0 Likes
Quoting: dpanterCan't wait to try it, some games implement tragically bad AA.
FFXIV is one of those games. I recently unsubbed because the game is too painful to look at. So many jaggies and shimmering. Really ruins my enjoyment of the game.
One can only hope they will implement it. I don’t think with FSR 2.0 we can force insert it with proton.
1 Likes, Who?
Quoting: Doc AngeloThe meaning of the terms around "artificial intelligence" are weird
"Machine Learning" is a huge pile of buzzword/b*llsh*t bingo. That's just how it is.
1 Likes, Who?
QuoteDelivers similar or better than native image quality using temporal data
Wait, so it can make an image that's better than the original??
0 Likes
Arehandoro Mar 17, 2022
I might be going blind, I don't see much difference between the 3 :(
1 Likes, Who?
Quoting: Doc AngeloHow can i use them just for antialiasing (without upscaling) ?Quoting: axredneckI mean more advanced techniques which not only remove ladders but try to reconstruct small details like wires.
You mean wires that turn up as visually disconnected pixel strings? You MUST use the technologies in question for that, AMD FidelityFX or Nvidia DLSS. That's pretty much what they are intended for.
(Especially for games that have neither DLSS/FSR nor antialiasing built in)
0 Likes
Patreon
PayPal
See more from me