NVIDIA reveals DLSS 2.0. The second-generation of the company's deep learning super sampling promises better image quality than its predecessor. DLSS uses artificial intelligence to upscale to a higher resolution and enhance image quality. Besides the promise of better image quality, one of the benefits of DLSS 2.0 is that the technique no longer needs to be trained on a per-game basis.
Interestingly, NVIDIA now claims that images rendered via DLSS 2.0 can sometimes look better than images rendered in native resolution. Some examples can be found at NVIDIA.
DLSS 2.0 offers several key enhancements over the original version:
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.