RTX Video Super Resolution is a new AI upscaling tool from Nvidia, though it’s not meant to make your games look or run better. However, it will still be very useful for gamers as it takes regular 1080p videos from your browser and converts them to 4K.
The new tool uses AI to improve video streaming quality for owners of recent Nvidia graphics cards. It works by removing blocky compression artifacts and then upscaling the video resolution, thus cleaning up the input and then blowing it up to the big screen. From Nvidia’s videos of the feature so far, the only option seems to be 1080p -> 4K upscaling.
Nvidia says the end result should offer a big improvement to video clarity on high-resolution screens, where the image could otherwise look a bit degraded from wear and tear.
The company’s CES 2023 Special Address featured an Apex Legends clip that looked a lot better with RTX Video Super Resolution enabled. I hope it is just as impressive universally.
RTX Video Super Resolution launches in February and I’d like to try it out for myself when this feature is available. I wonder how well it works on all the different types of video. Will it work best on gameplay videos, where Nvidia has already shown its expertise with its Deep Learning Super Sampling (DLSS) feature, or is the upscaling algorithm smart in ways beyond just rendered frames? I’d like to try it out on a beautiful view of a national park and see how it goes.
The new feature works within the Chrome and Edge browsers and also requires an Nvidia RTX 30 Series or 40 Series GPU to function. Nvidia hasn’t specified exactly what is required of those two generations of GPU for the new upscaling feature to work, nor whether there’s any performance impact, but at least this isn’t a 40-series feature.
Scaling up really is it future of PC performance (opens in new tab)and it was only a matter of time before someone turned the attention of one of these clever algorithms to our binge-watching habits.