NVIDIA has officially announced DLSS 2.0. This is an improved version of its Deep Learning Super Sampling process, which leverages the power of artificial intelligence to create high-quality images with fewer rendered pixels.
According to NVIDIA, DLSS 2.0 is capable of offering image quality that’s comparable to native resolution “while rendering only one quarter to one half of the pixels.” That’s a pretty bold statement, but the company has provided plenty of comparisons to back up that claim.
Control running under DLSS 2.0’s Quality Mode, for one, looks much sharper than the original thanks to temporal feedback techniques, bringing the game closer to its native fidelity. This mode boosts performance by as much as 76 percent at 1920 x 1080 and 2560 x 1440, while Performance Mode delivers gains of 2-3x at 4K (3840×2160).
Here are the key enhancements of DLSS 2.0 over the original version. Be sure to check out NVIDIA’s original article, which offers additional comparisons for Deliver Us The Moon, MechWarrior 5: Mercenaries, and Wolfenstein: Youngblood.
Superior Image Quality – DLSS 2.0 offers image quality comparable to native resolution while rendering only one quarter to one half of the pixels. It employs new temporal feedback techniques for sharper image details and improved stability from frame to frame.
Great Scaling Across All GeForce RTX GPUs and Resolutions – A new AI network more efficiently uses Tensor Cores to execute 2X faster than the original. This improves frame rates and eliminates previous limitations on which GPUs, settings, and resolutions could be enabled.
One Network For All Games – The original DLSS required training the AI network for each new game. DLSS 2.0 trains using non-game-specific content, delivering a generalized network that works across games. This means faster game integrations, and ultimately more DLSS games.
Customizable Options – DLSS 2.0 offers users 3 image quality modes – Quality, Balanced, Performance – that control the game’s internal rendering resolution, with Performance mode enabling up to 4X super resolution (i.e. 1080p → 4K). This means more user choice, and even bigger performance boosts.