Feature tests are special tests designed to highlight specific techniques, functions or capabilities.
The NVIDIA DLSS feature test is designed to help you test and compare the performance and image quality of DLSS processing.
|Feature test||3DMark NVIDIA DLSS feature test|
|Target hardware||NVIDIA GPUs that support DirectX Raytracing and DLSS|
|Graphics API||DirectX 12 with DirectX Raytracing|
You can choose to run the NVIDIA DLSS feature test using DLSS 2 or DLSS 1. With DLSS 2, you can also choose between three image quality modes—Quality, Performance and Ultra Performance.
The NVIDIA DLSS feature test runs the Port Royal benchmark twice. The first run has DLSS disabled to provide a baseline. The second run uses DLSS processing. The result screen reports the frame rate for each run.
DLSS is a proprietary NVIDIA technology. To run this test, you will need an NVIDIA graphics card with drivers that support DLSS and Microsoft DirectX Raytracing, such as a GeForce RTX series, Quadro RTX series or TITAN RTX. You must also have the latest NVIDIA drivers for your graphics card and the Windows 10 October 2018 Update (1809).
What is Deep Learning Super Sampling?
Deep Learning Super Sampling (DLSS) is an NVIDIA RTX technology that uses deep learning and AI to improve game performance while maintaining visual quality.
DLSS uses a deep neural network to extract multidimensional features of the rendered scene and intelligently combine details from multiple frames to construct a high-quality final image. This approach allows NVIDIA RTX GPUs to use fewer samples for rendering and use AI to fill in the information to create the final image. The result is a clear, crisp image of a quality similar to traditional rendering but with higher performance.
DLSS 2 is an improved version of DLSS that aims to deliver more performance and image quality than the original DLSS.
Aliasing—a distracting jagged line on the edge of an object in a scene—is a common artifact in real-time computer graphics.
Increasing the resolution of the entire image is not always practical so a common way to remove the jagged lines is to increase the number of samples on the line which helps to smooth it. Many techniques have been developed which intelligently blend the colors of the jagged edges with the colors of nearby pixels but most of these can lead to a loss of fine detail.
The 3DMark Port Royal benchmark uses Temporal Anti-Aliasing (TAA), a popular anti-aliasing technique used in many games today. TAA solves the aliasing problem by accumulating multiple samples temporally—instead of adding more samples to a single frame, it adds a small jitter to a rendered frame and combines the current samples with matching samples from previous frames. This directly leads to an increased sampling rate. Unfortunately, TAA suffers from flickering and ghosting artifacts. These artifacts are more visible in dynamic scenes.
A deep learning solution to aliasing
To develop Deep Learning Super Sampling, NVIDIA researchers trained a neural network to find jagged edges in an image, determine the best color for each pixel, and then apply proper colors to create smoother edges and improved image quality.
DLSS provides high-quality anti-aliasing with fewer artifacts and better performance than other types of anti-aliasing. Compared with TAA, DLSS produces sharp images that are temporally stable.
Neural network training
The specific details and method of the training is NVIDIA's trade secret since DLSS is a proprietary technology.
The original DLSS version required training the AI network with specific data extracted from each supported title. DLSS 2 does not require any input from the workload to train the network. It delivers a generalized network that can work across games.