|
'''Deep learning super sampling''' ('''DLSS''') is a family of [[Real-time computing|real-time]] [[deep learning]] image enhancement and [[Image scaling|upscaling]] technologies developed by [[Nvidia]] that are available in a number of [[video game]]s. The goal of these technologies is to allow the majority of the [[graphics pipeline]] to run at a lower [[Display resolution|resolution]] for increased performance, and then infer a higher resolution image from this that approximates the same level of detail as if the image had been rendered at this higher resolution. This allows for higher graphical settings and/or [[frame rates]] for a given output resolution, depending on user preference.<ref name=":2">{{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|access-date=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>
All generations of DLSS are available on all [[Nvidia RTX|RTX]]-branded cards from Nvidia in supported titles. However, the [[Frame Generation]] feature is only supported on [[GeForce 40 series|40 series]] GPUs or newer and [[Multi- Frame Generation]] is only available on [[GeForce 50 series|50 series]] GPUs.<ref name=":3">{{Cite web |title=Introducing NVIDIA DLSS 3 |url=https://www.nvidia.com/en-us/geforce/news/dlss3-ai-powered-neural-graphics-innovations/ |access-date=2022-09-20 |website=NVIDIA |language=en-us}}</ref><ref name=":6">{{Cite web |title=NVIDIA DLSS 4 Introduces Multi Frame Generation & Enhancements For All DLSS Technologies |url=https://www.nvidia.com/en-us/geforce/news/dlss4-multi-frame-generation-ai-innovations/ |access-date=2025-01-14 |website=NVIDIA |language=en-us}}</ref> Nvidia has also introduced '''Deep learning dynamic super resolution''' ('''DLDSR'''), a related and opposite technology where the graphics are rendered at a higher resolution, then downsampled to the native display resolution using an [[artificial intelligence]]-assisted downsampling algorithm to achieve higher image quality than rendering at native resolution.<ref>{{cite web |last1=Archer |first1=James |title=Nvidia DLDSR tested: better visuals and better performance than DSR |url=https://www.rockpapershotgun.com/nvidia-dldsr-tested-better-visuals-and-better-performance-than-dsr |website=Rock Paper Shotgun |date=17 January 2022 |access-date=23 February 2022 |ref=dldsr}}</ref>
== History ==
|4.0
|January 2025
|DLSS 4.0 adds Multi- Frame Generation, new AI-model based on the [[Transformer (deep learning architecture)|transformer architecture]], improving frame stability, reduced memory usage, and increased lighting detail.<ref name=":6" /><ref>{{Cite web |last=Khan |first=Sarfraz |date=2025-01-14 |title=NVIDIA Confirms Updated DLSS Frame Generation On RTX 40 GPUs, Leads to Lower VRAM Usage & Faster Performance |url=https://wccftech.com/nvidia-dlss-frame-generation-rtx-40-gpus-new-ai-model-faster-lower-vram-requirement/ |access-date=2025-01-14 |website=Wccftech |language=en-US}}</ref>
|}
=== DLSS 4.0 ===
The fourth generation of [[Deep Learning Super Sampling]] (DLSS) was unveiled alongside the [[GeForce 50 series]]. DLSS 4 upscaling uses a new vision [[Transformer (deep learning architecture)|transformer]]-based model for enhanced image quality with reduced ghosting and greater image stability in motion compared to the previous [[convolutional neural network]] (CNN) model.<ref>{{cite web |last1=Leadbetter |first1=Richard |date=January 7, 2025 |title=Hands-on with DLSS 4 on Nvidia's new GeForce RTX 5080 |url=https://www.eurogamer.net/digitalfoundry-2025-hands-on-with-dlss-4-on-nvidias-new-geforce-rtx-5080 |website=Eurogamer |language=en-GB |access-date=January 7, 2025}}</ref> DLSS 4 allows a greater number of frames to be generated and [[Frame interpolation|interpolated]] based on a single traditionally rendered frame. This form of frame generation called Multi- Frame Generation is exclusive to the GeForce 50 series while the [[GeForce 40 series]] is limited to one interpolated frame per traditionally rendered frame. According to Nvidia, this technique will increase performance by up to 800% while retaining low latency with [[Nvidia Reflex]].<ref name=":62">{{Cite web |title=NVIDIA Blackwell GeForce RTX 50 Series Opens New World of AI Computer Graphics |url=https://nvidianews.nvidia.com/news/nvidia-blackwell-geforce-rtx-50-series-opens-new-world-of-ai-computer-graphics |access-date=2025-01-07 |website=NVIDIA Newsroom |language=en-us}}</ref> Nvidia claims that DLSS 4x Frame Generation model uses 30% less video memory with the example of ''[[Warhammer 40,000: Darktide]]'' using 400MB less memory at 4K resolution with Frame Generation enabled.<ref>{{cite web |last1=Lin |first1=Henry |last2=Burnes |first2=Andrew |date=January 6, 2025 |title=Nvidia DLSS 4 Introduces Multi Frame Generation & Enhancements For All DLSS Technologies |url=https://www.nvidia.com/en-us/geforce/news/dlss4-multi-frame-generation-ai-innovations/ |website=Nvidia |language=en-US |access-date=January 7, 2025}}</ref> Nvidia claims that 75 games will integrate DLSS 4 Multi- Frame Generation at launch, including ''[[Alan Wake 2]]'', ''[[Cyberpunk 2077]]'', ''[[Indiana Jones and the Great Circle]]'', and ''[[Star Wars Outlaws]]''.<ref>{{cite web |last1=Mujtaba |first1=Hassan |date=January 6, 2025 |title=Nvidia DLSS 4 Delivers An Insane 8x Performance Boost Versus DLSS 3 With Multi Frame Generation Technology, Enhanced Upscaling For RTX 20 & Above |url=https://wccftech.com/nvidia-dlss-4-8x-faster-dlss-3-multi-frame-generation-enhanced-upscaling-rtx-20-above/ |website=Wccftech |language=en-US |access-date=January 7, 2025}}</ref>
{| class="wikitable plainrowheaders" style="text-align:left; font-size:90%;
|
