TechWatch

DLSS 2.0 is a big leap in rendering

The basic concept of Deep Learning Super Sampling—DLSS—is just what its name implies. Nvidia trains a deep learning AI model with very high-quality images on a supercomputer and provides that model along with their GPU driver. Games use that model during gameplay to create a higher resolution image using computations based on lower resolution game renders along with the power ...

Jon Peddie

The basic concept of Deep Learning Super Sampling—DLSS—is just what its name implies. Nvidia trains a deep learning AI model with very high-quality images on a supercomputer and provides that model along with their GPU driver. Games use that model during gameplay to create a higher resolution image using computations based on lower resolution game renders along with the power of the AI (details described below). Lowering the compute requirements in the GPU allows for a higher frame rate—in some cases over 2× higher. Other image scaling techniques can offer similar speedups but have a loss of image quality relative
...

Enjoy full access with a TechWatch subscription!

TechWatch is the front line of JPR information gathering service, comprising current stories of interest to the graphics industry spanning the core areas of graphics hardware and software, workstations, gaming, and design.

A subscription to TechWatch includes 4 hours of consulting time to be used over the course of the subscription.

Already a subscriber? Login below

This content is restricted

Subscribe to TechWatch