NVIDIA has unveiled its new RTX Video Super Resolution technology at CES 2023, which will help owners of GeForce RTX 4000 and 3000 series graphics cards upscale via videos starting next month. The technology is said to work in Google&s Chrome and Microsoft&s Edge browsers and be able to upscale the resolution of videos played in the browser and clean up compression artifacts via 
Super Resolution AI. The tool uses the Tensor cores of modern RTX 3000/4000 GeForce GPUs, which were especially developed for AI functions.
NVIDIA RTX Video Super Resolution
The algorithm is said to work with videos with a native resolution of 360p to 1440p and a frame rate of up to 144Hz in real time, so 1080p videos - as seen in the sample clip - can be upscaled to a resolution of 4K, significantly improving their image quality on large displays with the appropriate resolution and eliminating staircase-like artifacts due to the comparatively primitive upscaling of TVs or video players.
What is Super Resolution?
While the rule used to be that when resolution was increased, no detail could be added that was not in the original image, a paradigm shift has been taking place for several years. Thanks to new super-resolution technology, more detail can be added to an image than was originally available in digital form. But how is this possible?
Super Resolution methods, increase the resolution of an image and use for the "more pixels" and thus more image information not the rather primitive interpolation between known pixels, but invent details conclusively.
This is made possible by Deep Learning technology, as these AI algorithms are very good at recognizing and meaningfully adding objects thanks to training with millions of images. When upscaling, neural networks make use of the typical patterns of natural objects - i.e. structures in the low-resolution images are reconstructed in a meaningful way when upscaling. So, for example, if a corresponding Super Resolution AI has seen millions of faces from different angles and in diverse lighting situations, it can subsequently add learned appropriate details to each coarse resolution-only face in an image. However, this is just as true for plants, cars, or animals.
NVIDIA RTX Video Super Resolution
RTX Video Super Resolution Tool starting in February
.
Users with the appropriate NVIDIA hardware can use the Super Resolution technology to, for example, upscale FullHD videos from Netflix base or standard subscriptions to 4K without having to sign up for the more expensive premium subscription. Another use case are (old) YouTube videos that are only available in low resolution.
Bild zur Newsmeldung:
;)
;)
;)