Deep Learning Super Sampling: Difference between revisions

Revision as of 03:56, 13 April 2020

Revision as of 21:29, 13 April 2020

Line 1:

{{Contradict|date=April 2020}}

'''Deep Learning Super Sampling''' (or '''DLSS''') is a technology developed by [[Nvidia]], using [[Deep learning]] to produce an image that looks like a higher-resolution image of the original image at a lower resolution. This technology is advertised as allowing to have a much higher resolution as the original without the [[Video card]] overhead.<ref>{{cite web|url=https://www.digitaltrends.com/computing/everything-you-need-to-know-about-nvidias-rtx-dlss-technology/|title=Nvidia RTX DLSS: Everything you need to know |publisher=[[Digital Trends]]|date=2020-02-14|accessdate=2020-04-05|quote=''Deep learning super sampling uses artificial intelligence and machine learning to produce an image that looks like a higher-resolution image, without the rendering overhead. Nvidia’s algorithm learns from tens of thousands of rendered sequences of images that were created using a supercomputer. That trains the algorithm to be able to produce similarly beautiful images, but without requiring the graphics card to work as hard to do it.''}}</ref>

{{Weasel|date=April 2020}}

'''Deep Learning Super Sampling''' (or '''DLSS''') is a technology developed by [[Nvidia]], using [[Deep learning]] to produce an image that looks like a higher-resolution image of the original image at a lower resolution.{{Contradict-inline|date=April 2020}} This technology is advertised as allowing to have a much higher resolution as the original without the [[Video card]] overhead.{{Ambiguous|date=April 2020}}<ref>{{cite web|url=https://www.digitaltrends.com/computing/everything-you-need-to-know-about-nvidias-rtx-dlss-technology/|title=Nvidia RTX DLSS: Everything you need to know |publisher=[[Digital Trends]]|date=2020-02-14|accessdate=2020-04-05|quote=''Deep learning super sampling uses artificial intelligence and machine learning to produce an image that looks like a higher-resolution image, without the rendering overhead. Nvidia’s algorithm learns from tens of thousands of rendered sequences of images that were created using a supercomputer. That trains the algorithm to be able to produce similarly beautiful images, but without requiring the graphics card to work as hard to do it.''}}</ref>

==History==

Nvidia advertised DLSS as a key feature of the [[GeForce 20 series|GeForce RTX 20]] series GPUs when they launched in September 2018.<ref name="techspot">{{cite web|url=https://www.techspot.com/article/1992-nvidia-dlss-2020/|title=Nvidia DLSS in 2020: stunning results|publisher=techspot.com|date=2020-02-26|accessdate=2020-04-05}}</ref> At that time, the results were limited to a few video games (namely [[Battlefield V]]<ref>{{cite web|url=https://www.techspot.com/article/1794-nvidia-rtx-dlss-battlefield/|title=Battlefield V DLSS Tested: Overpromised, Underdelivered|publisher=techspot.com|date=2019-02-19|accessdate=2020-04-06|quote=''Of course, this is to be expected. DLSS was never going to provide the same image quality as native 4K, while providing a 37% performance uplift. That would be black magic. But the quality difference comparing the two is almost laughable, in how far away DLSS is from the native presentation in these stressful areas.''}}</ref> and [[Metro Exodus]]) because the algorithm had to be trained specifically on each game on which it was applied and the results were usually not as good as simple resolution upscaling.<ref>{{cite web|url=https://www.techquila.co.in/nvidia-dlss-vs-taa/|title=AMD Thinks NVIDIA DLSS is not Good Enough; Calls TAA & SMAA Better Alternatives|publisher=techquila.co.in|date=2019-02-15|accessdate=2020-04-06|quote=''Recently, two big titles received NVIDIA DLSS support, namely Metro Exodus and Battlefield V. Both these games come with NVIDIA’s DXR (DirectX Raytracing) implentation that at the moment is only supported by the GeForce RTX cards. DLSS makes these games playable at higher resolutions with much better frame rates, although there is a notable decrease in image sharpness. Now, AMD has taken a jab at DLSS, saying that traditional AA methods like SMAA and TAA “offer superior combinations of image quality and performance.”''}}</ref><ref name="kotaku">{{cite web|url=https://www.kotaku.com.au/2020/02/nvidia-rtx-dlss-quietly-got-a-hell-of-a-lot-better/|title=Nvidia Very Quietly Made DLSS A Hell Of A Lot Better|publisher=[[Kotaku]]|date=2020-02-22|accessdate=2020-04-06|quote=''The benefit for most people is that, generally, DLSS comes with a sizeable FPS improvement. How much varies from game to game. In Metro Exodus, the FPS jump was barely there and certainly not worth the bizarre hit to image quality.''}}</ref>

In 2019, the videogame [[Control (video game)|Control]] shipped with [[Ray tracing (graphics)|Ray tracing]] and an improved version of DLSS, but which didn't use Deep learning.<ref name="eurogamer">{{Contradict-inline|date=April 2020}}

{{cite web|url=https://www.eurogamer.net/articles/digitalfoundry-2020-control-dlss-2-dot-zero-analysis|title=Remedy's Control vs DLSS 2.0 - AI upscaling reaches the next level |publisher=[[Eurogamer]]|date=2020-04-04|accessdate=2020-04-05|quote=''Of course, this isn't the first DLSS implementation we've seen in Control. The game shipped with a decent enough rendition of the technology that didn't actually use the machine learning''}}</ref><ref>{{cite web|url=https://www.techquila.co.in/nvidia-dlss-2-update-rtx-tensor-cores/|title=NVIDIA DLSS 2.0 Update Will Fix The Geforce RTX Cards’ Big Mistake|publisher=techquila.co.in|date=2020-03-24|accessdate=2020-04-06|quote=''As promised, NVIDIA has updated the DLSS network in a new Geforce update that provides better, sharper image quality while still retaining higher framerates in raytraced games. While the feature wasn’t used as well in its first iteration, NVIDIA is now confident that they have successfully fixed all the issues it had before''}}</ref>

In April 2020, Nvidia advertised an improved version of DLSS named DLSS 2.0, which would come for upcoming games, which this time is said to use machine learning and don't need to be trained on every game it is applied to.{{Weasel inline|date=April 2020}}<ref name="techspot"/> Benchmarks on [[Control (video game)|Control]] tend to show that the resulting image at a 1080 pixels [[Image resolution|resolution]] upscaled from a 720 pixels resolution have the same quality as a native 1080 pixels resolution but retain the 720 pixels resolution performance.<ref>

{{cite web|url=https://www.techquila.co.in/nvidia-dlss-2-control-review/|title=NVIDIA DLSS 2.0 Review with Control – Is This Magic?|publisher=techquila.co.in|date=2020-04-05|accessdate=2020-04-06}}</ref>{{Not in citation given}} A side effect of DLSS 2.0 is that it seems not to work very well with [[Spatial anti-aliasing|anti-aliasing]] techniques such as [[Multisample anti-aliasing|MSAA]] or [[Intellisample|TSAA]], the performance being very negatively impacted if these techniques are enabled on top of DLSS.<ref>{{cite web|url=https://hothardware.com/reviews/investigating-nvidia-dlss-20-in-mechwarrior-5-and-control|title=Evaluating NVIDIA DLSS 2.0 Quality And Performance In Mech 5 And Control|publisher=hothardware.com|date=2020-03-27|accessdate=2020-04-07|quote=''One side effect of DLSS is that it doesn't seem to play nicely with MSAA (forced through the drivers) or TXAA enabled in the game. Performance actually tanked pretty hard with either of those anti-aliasing methods on top of DLSS 2.0, with the Quality mode only performing around half as fast as no DLSS''}}</ref>

As of April 2020, DLSS 2.0 must still be included per game basis by the [[Video game developer|game developers]].