It’s been close to a year since NVIDIA released the 2nd generation of its DLSS (Deep Learning Super Sampling) technology, otherwise known as DLSS 2.0. While DLSS 1.0 had faced criticisms on the lack of games it supports, DLSS 2.0 has been well-received by the community as it promises greater impact on gaming experience.
DLSS 2.0 is a new and improved deep learning neural network that boosts frame rates while generating beautiful, crisp game images. DLSS 2.0 still utilizes the on-board Tensor cores, just obviously with better efficiency and execution than its predecessor. The algorithm still employs the use of machine learning but this time, the AI did not need to be trained specifically on each game.
To help you further understand, here are 5 things that you need to know about NVIDIA’s DLSS 2.0 technology so you can decide for yourself if it’s time to upgrade to a new RTX 30 Series GPU.
1. Provides Better Image Quality and More Details
DLSS 2.0 offers image quality comparable to native resolution while rendering only one-quarter to one-half of the pixels. This boosts performance by a significant degree and it’s anti-aliasing has better temporal stability and image clarity compared to commonly-used Temporal Anti-Aliasing (TAA) techniques.
2. It’s Less Demanding on GPU
Most are familiar with standard super sampling— a technique where you have a game running at a higher internal resolution than what the monitor can support, but then down scales the image to fit the display. Although it’s very computationally taxing, it can provide a significant quality boost that other anti-aliasing methods may not be able to achieve. DLSS 2.0 however, is quite different from standard super sampling, and it’s actually less demanding on the GPU.
Instead of forcing the GPU to render higher resolution frames from scratch, it uses a generalized neural network to predict what the frame should look like. The supercomputer has done the hard work already so the GPU doesn’t need to work as hard. It is extremely impressive and cutting edge technology.
3. Generalized Neural Network and NVIDIA’s Supercomputers
The original version of DLSS required training the AI network for each new game. Now instead of needing to separately train for every game, DLSS 2.0 uses more general visual content that’s more representative of a variety of different games. This means faster game integrations, and ultimately more games will end up supporting DLSS.
DLSS uses the power of NVIDIA’s supercomputers that runs games at very high resolutions and “remembers” what games look like at their best. This information is then fed back to the PC and the graphics card then uses this information as a cheat sheet to upgrade what it renders. This enables the graphics card to just render a lower resolution, allowing the game to run on a weaker computer at a higher framerate. These lower resolution images/video is then fed into the machine learning then returns a higher quality version of those images/video instead. This means you get the power of the DLSS supercomputer network to help you boost performance and resolution.
4. Customizable Options
Among the benefits is the ability to upscale frames by up to 4X the sample resolution (i.e. 1080p → 4K). DLSS 1.0 only allowed for 2X upscales. As a result, the algorithm offers more scaling options and gamers will be able to choose between Performance, Balanced, and Quality, each focusing the RTX GPU’s Tensor core horsepower on a different aspect of DLSS.
5. Offers a Free Plugin via the Unreal Engine Marketplace
To bring DLSS to more games and gamers, NVIDIA have recently released DLSS as a free plugin via the Unreal Engine marketplace. Unreal Engine 4 is the gaming industry’s most used engine, powering hundreds of titles and thousands of indie projects. Now that the plugin is available, developers making projects in Unreal Engine 4 can “start using DLSS right away,” said Henry Lin, senior product manager at NVIDIA. Adding DLSS support to a game will probably take a bit more time and effort from the developers, but Lin said that NVIDIA has “been able to fine tune the integration to work well out of the box for the vast majority of content.
Like with other NVIDIA features such as ray tracing, DLSS is only available on the RTX 20 and 30 series of graphics cards. Also keep in mind that while DLSS cuts down on hardware strain, it’s not magic and you still want a decently powerful PC. If you’re somebody with a fancy new 4K TV or monitor then DLSS is a great tool to keep games running smooth while taking advantage of that sweet higher resolution. We hope this list helped you think through the many advantages of the DLSS 2.0 technology offered by NVIDIA.
What are your thoughts?
