Today’s article is going to cover everything.
Then, of course, there will be a look at performance across all of Nvidia’s RTX GPUs.
Strap yourselves in because this is going to be a comprehensive look at where DLSS stands today.
This AI algorithm also leveraged a new feature on RTX Turing GPUs: the tensor cores.
While all this sounded promising, the execution within the first 9 months was far from perfect.
Early DLSS implementations looked bad, producing a blurry image with artifacts.
Battlefield V was a particularly egregious case, but even Metro Exodus failed to impress.
Theimplementation in Battlefield V, for example, looked worse and performed worse than a simple resolution upscale.
InMetro Exodusit was more on par with these techniques, but it wasn’t impressive either.
The first step towards DLSS 2.0 was the release of Control.
We’ll be focusing primarily on Youngblood as it’s a major release.
Control + DLSS
With a target resolution of 4K, DLSS 1.9 in Control is impressive.
More so when you consider this is an approximation of the full technology running on the shader cores.
DLSS with a 1440p render resolution is the better of the two options.
It’s also close overall to a scaled 1800p image.
The output quality is very good.
We can also see that DLSS rendering at 1440p is better than simply playing the game at 1440p.
But the key difference between older versions of DLSS and this new version, is the performance.
… the key difference between older versions of DLSS and this new version, is the performance.
Previously, running DLSS came with a performance hit relative to whatever resolution it was rendering at.
However, this shader processed version is significantly less performance intensive.
You’ll notice that we haven’t mentioned image sharpening and how that factors in.
The results were better.
Using DLSS with a target resolution below 4K is also not a good idea.
Even the higher quality option, 960p, delivered far from a native 1440p image.
This algorithmic approximation of DLSS is just not suited to these lower resolutions.
The performance gains we see with each RTX GPU are fairly consistent across the board.
This first batch of results playing Control with the shader version of DLSS are impressive.
Not needing per-game training for DLSS 2.0 is huge…
Not needing per-game training for DLSS 2.0 is huge.
This has provided better image quality, but it also gives Nvidia another advantage: generalized DLSS updates.
We’ll see whether that materializes, but it’s an improvement over what was previously possible.
Another benefit from not needing per-game training is that it makes DLSS faster and easier to integrate.
This should mean more DLSS games, but we’ll wait and see to see if that materializes first.
In fact, DLSS 2.0 is extremely impressive, far exceeding our expectations for this sort of upscaling technology.
When targeting a native 4K resolution, DLSS 2.0 delivers image quality equivalent to the native presentation.
We suspect with a really good post-process anti-aliasing like we’ve seen in some other games (e.g.
Shadow of the Tomb Raider), we’d see DLSS and native 4K looking almost identical.
None of those issues are present here, this just straight up looks like a native image.
We should stress that native 4K and DLSS 4K don’t look identical.
This isn’t a black box algorithm that can magically pull true native 4K out of the hat.
This is because Nvidia trains the AI using super sampled images with the clearest possible forms of these details.
But these are minor issues and a far cry from the problems with DLSS 1.0.
Quality is slightly sharper than Balanced, which is slightly sharper than Performance.
The other really impressive aspect to DLSS 2.0 is that it’s also fully functional at lower resolutions.
Take 1440p for example.
Even with Control’s shader implementation this was a significant issue, but it’s not with DLSS 2.0.
At 1440p the limitations of the lower quality DLSS modes does become a bit more apparent.
Quality is the mode we would opt to use at 1440p given it delivers the closest presentation to native.
All of these modes we’d say deliver image quality essentially identical to native 4K, if not better.
This chart shows the actual results from all six GPUs, and you’ll see the lines match up.
What about at 1440p?
Clearly we aren’t getting as good performance gains here.
The Quality mode provided a 16% gain on average, and the Balanced mode a 23% gain.
On the other hand, we saw larger gains when ray tracing was enabled.
After analyzing DLSS in Youngblood, there’s no doubt that the technology works.
It’s mind blowing.
It’s also exactly what Nvidia promised at launch.
We’re just glad we’re finally getting to see that now.
This is almost an identical situation toNvidia’s RTX ray tracing.
The huge slate of DLSS games is almost laughable in 2020 with most of these never getting DLSS.
Those are some major releases that Nvidia advertised would support DLSS but never came to fruition.
Well, a year later and it hasn’t improved in these games at all.
DLSS is at a tipping point.
