Info NVIDIA Details New DLSS Technique in Control, Explains How DLSS Can Further Improve in the Future

[happy medium]

During our research, we found that certain temporal artifacts can be used to infer details in an image. Imagine, an artifact we’d normally classify as a “bug,” actually being used to fill in lost image details. With this insight, we started working on a new AI research model that used these artifacts to recreate details that would otherwise be lost from the final frame.

This AI research model has made tremendous progress and produces very high image quality. However, we have work to do to optimize the model’s performance before bringing it to a shipping game.

Leveraging this AI research, we developed a new image processing algorithm that approximated our AI research model and fit within our performance budget. This image processing approach to DLSS is integrated into Control, and it delivers up to 75% faster frame rates.

https://wccftech.com/nvidia-details...s-how-dlss-can-further-improve-in-the-future/



You cannot drop links and post only what's in the article. You need to post your own commentary.
Also when you post about an article, the publications name needs to be in the title.


esquared
Anandtech Forum Director

 

[Krteq]

Well, NV is trying hard to promote DLSS via PR and marketing materials ... but it still suffers from artifacts and all the same issues we seen before

For example, if shadows appear frayed, the effect with DLSS usually increases significantly. And fence-like objects that are no longer displayed perfectly even without DLSS, then suddenly frayed with the feature or are sometimes no longer displayed. With DLSS, Control is showing even more graphics errors than it already does, which is not very conducive to graphics quality. The bottom line is that if the video card renders in the same resolution once with and once without DLSS, the result is different but not better.
....
Nvidia has integrated DLSS as a remedy. In principle this works quite well in Control and brings a big FPS boost. Sometimes even the blur is reduced, with some objects then appear overshadowed and flicker. However, DLSS is quite allergic to the game's graphics flaws, and they are made worse by AI upscaling. First of all, using ray tracing to make the graphics more realistic, but then to incorporate further errors with DLSS does not work.

ComputerBase.de - Control mit RTX & DLSS im Test: Raytracing, DLSS und das Fazit

 

[Dribble]

Well, NV is trying hard to promote DLSS via PR and marketing materials ... but it still suffers from artifacts and all the same issues we seen before

One would think you could use both techniques - use the sharpening filter first so the starting point is really good and then use DLSS based off that?

 

[Det0x]

I gonna copy some interesting posts from beyond3d
Turns out it's more than likely that control are using basic upscaling and not DLSS at all

NVIDIA claims they developed a new algorithm for Control, and intend to use it for future titles.

Most importantly, it's not DLSS but a 'conventional' image-processing algorithm. "Hand engineered algorithms are fast and can do a fair job of approximating AI." Their improved DLSS system is too slow using ML so they're using a compute based solution that approximates the AI results.

The plan is to get the AI fast enough to give better results, but Control's implementation isn't ML and is much lower impact, which is by-and-large what games need. They don't need perfect, but good enough at fast enough speeds. So Control is actually a +1 for algorithmic reconstruction methods, with ML contributing to the development of the algorithm.

The message behind this twisted marketing way of saying things indirectly is quite interesting, but no surprise

Yeah that Nvidia article is really focused on promoting "DLSS" and Turing's tensor cores whilst dancing around the fact that Control doesn't seem to use either.

You take that at meaning they aren't being used in Control? lol no. They're saying those cores are there and they're capable of the next round of improvements coming to DLSS which is a more optimized version of their AI research model. It's also a way of reassuring people that they wont need a next gen GPU to handle these improvements when they come. Their AI model utilizes deep learning to train their Image Processing algorithm. The goal is to get that high quality of the AI model performant enough so that it can run on the tensor cores.

I disagree for several reasons.

1. All previous DLSS implementations have been rather expensive. Suddenly this one has the same performance as basic upscaling.
2. The various selectable resolutions from which to upscale resulting in more combinations to train than previous titles.
4. Its now usable at all performance levels and provides an improvement regardless of how long other parts of the GPU require to process a frame.
3. There would be no need for the article.

They mention performance budget but they dont reference tensor cores at all in that context. Its certainly possible they are being used but if i had to bet given the available info, id bet against.

The full discussion can be found here

 

[maddie]

I gonna copy some interesting posts from beyond3d
Turns out it's more than likely that control are using basic upscaling and not DLSS at all



Most importantly, it's not DLSS but a 'conventional' image-processing algorithm. "Hand engineered algorithms are fast and can do a fair job of approximating AI." Their improved DLSS system is too slow using ML so they're using a compute based solution that approximates the AI results.

The plan is to get the AI fast enough to give better results, but Control's implementation isn't ML and is much lower impact, which is by-and-large what games need. They don't need perfect, but good enough at fast enough speeds. So Control is actually a +1 for algorithmic reconstruction methods, with ML contributing to the development of the algorithm.



Yeah that Nvidia article is really focused on promoting "DLSS" and Turing's tensor cores whilst dancing around the fact that Control doesn't seem to use either.



I disagree for several reasons.

1. All previous DLSS implementations have been rather expensive. Suddenly this one has the same performance as basic upscaling.
2. The various selectable resolutions from which to upscale resulting in more combinations to train than previous titles.
4. Its now usable at all performance levels and provides an improvement regardless of how long other parts of the GPU require to process a frame.
3. There would be no need for the article.

They mention performance budget but they dont reference tensor cores at all in that context. Its certainly possible they are being used but if i had to bet given the available info, id bet against.

The full discussion can be found here

What a quote.

"Hand engineered algorithms are fast and can do a fair job of approximating AI"

So real I, is faster and can approximate synthetic I. I thought it was the other direction.

 

[Det0x]

DLSS is Dead: New Nvidia Freestyle Sharpening Tested @ techspot

Overall we think this situation is really interesting. AMD introducing RIS may have forced Nvidia to act in updating their sharpening filter available through Freestyle. In the process, they have created a better solution than DLSS which was advertised as a key selling point for RTX graphics cards. Big win for gamers.
.
.
Does this mean Nvidia should kill DLSS entirely? Hard to suggest they would do so, but we're certain that for enthusiasts reading this kind of coverage, you know that using resolution downsampling plus Nvidia’s Freestyle sharpening filter is the best option, effectively killing DLSS if you know what you’re doing.