PC video streaming via Google Chrome and Microsoft Edge browsers gets a GeForce RTX size upgrade today with the release of RTX Video Super Resolution (VSR).

Almost 80% of Internet bandwidth today is taken up by streaming video. And 90% of that content is streamed in 1080p or lower, including popular sources like Twitch.tv, YouTube, Netflix, Disney+, and Hulu.

However, when viewers use displays above 1080p, as many PC users do, the browser must scale the video to match the display resolution. Most browsers use basic scaling techniques that result in soft or blurry final images.

With RTX VSR, users of GeForce RTX 40 and 30 series GPUs can use artificial intelligence to upscale low-resolution content to 4K according to the display resolution. AI removes blocky compression artifacts and improves video sharpness and clarity.

Just as putting on prescription glasses can instantly focus the world, RTX Video Super Resolution gives viewers on GeForce RTX 40 and 30 Series PCs a clear picture in the world of streaming video.

RTX VSR is now available as part of the latest GeForce Game Ready Driver, which provides the best experience for new games such as Atomic heart and FINAL closed beta version.

The evolution of AI scaling

AI upscaling is the process of converting lower resolution media to higher resolution by running low resolution images through a deep learning model to predict high resolution versions. To make these predictions with high accuracy, the neural network model must be trained on countless images of different resolutions.

4K displays can blur images because they have to stretch lower resolution images to fit the screen size. The use of artificial intelligence to enhance the quality of streaming video provides unparalleled clarity in low-resolution images.

The advanced AI model can capture low-resolution video and produce incredible sharpness and enhanced detail that no traditional scaler can reproduce. Edges look sharper, hair looks more tousled, and landscapes come through with stunning clarity.

In 2019, an early version of this technology was released TV SHIELD. It was a breakthrough that improved streaming content aimed at TVs, mostly in the 480p to 1080p range, and optimized for viewing from 10 feet away.

PC viewers typically sit much closer to their displays than TV viewers, requiring a higher level of processing and enhancement for scaling. With the GeForce RTX 40 and 30 series GPUs, users now have extremely powerful AI processors with tensor cores, enabling a new generation of AI scaling with RTX VSR.

How RTX Video Super Resolution works

RTX VSR is a breakthrough in AI pixel processing that significantly improves the quality of streaming video content in addition to edge detection and feature sharpening.

Blocky compression artifacts are a constant problem with video streaming. Whether it’s the fault of the server, the client, or the content itself, the problems are often exacerbated by traditional scaling, leaving viewers with a less pleasant visual experience.

Click the image to see the difference between bicubic scaling (left) and RTX Video Super Resolution.

RTX VSR reduces or eliminates artifacts caused by video compression, such as blockiness, ringing artifacts around edges, blurring of high-frequency details, and banding in flat areas, while reducing lost textures. It also sharpens edges and details.

The technology uses a deep learning network that performs scaling and compression artifact reduction in a single pass. The network analyzes the lower resolution video frame and predicts the afterimage at the target resolution. This residual image is then overlaid on the traditional scaled image, correcting artifact errors and sharpening the edges according to the original resolution.

A deep learning network is trained on a wide range of content with different levels of compression. It learns about the types of compression artifacts present in low-resolution or low-quality video that are otherwise absent in uncompressed images as a reference for training the network. A thorough visual evaluation is used to ensure that the generated model is effective for almost all real-world and in-game content.

Let’s start

RTX VSR requires a GeForce RTX 40 or 30 series GPU and works with almost all content streamed in Google Chrome and Microsoft Edge.

The feature also needs to be updated to the latest version GeForce Game Ready driveravailable today or next day Driver NVIDIA Studio issue in March. Both Chrome (version 110.0.5481.105 or later) and Edge (version 110.0.1587.56) have recently been updated to support RTX VSR.

To enable it, launch the NVIDIA Control Panel and open Video Image Settings. Check the resolution box under RTX Video Enhancement and choose a quality from one to four, from the least impact on GPU performance to the highest level of upscaling.

Learn more, including other setup configurations, here NVIDIA knowledge base article.