Replacing the usual denoising algorithms used to generate an image from the (usually small) number of traced rays in a scene with a new AI model that runs alongside DLSS upscaling, Nvidia is able to show ray traced reflections and shadows with less artifacts, significantly improved clarity, and more data points being represented (like soft shadows and small occlusions) at no penalty to performance.
Unlike frame generation, DLSS 3.5’s ray reconstruction will work on all RTX series cards, including the 2000 series. In one example, Nvidia shows how fast moving objects no longer leave trails of temporal artifacts when RT global illumination is enabled.
As always, this will require games to be updated to support the new features, and this can’t be enabled by a simple DLL swap. At the moment, a few games, including Alan Wake 2 and Cyberpunk 2077, are announced to be working on implementing DLSS 3.5.
As long as it works. DLSS was fantastic when it launched but future versions seem to be more and more sluggish.
