Pixel Perfect: RTX Video Super Resolution now available


Streaming video on PCs via Google Chrome and Microsoft Edge browsers gets a GeForce RTX-sized upgrade today with the release of RTX Video Super Resolution (VSR).

Almost 80% of internet bandwidth today consists of streaming video. And 90% of that content is streamed at 1080p or lower, including from popular sources like, YouTube, Netflix, Disney+, and Hulu.

However, when viewers use displays higher than 1080p – like many PC users – the browser has to scale the video to fit the resolution of the display. Most browsers use basic upscaling techniques that result in soft or blurry final images.

With RTX VSR, GeForce RTX 40 and 30 series GPU users can tap AI to upscale lower-resolution content up to 4K to match their screen resolution. The AI ​​removes blocky compression artifacts and improves video sharpness and clarity.

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

RTX VSR is now available as part of the latest GeForce Game Ready driver that provides the best experience for launching new games such as: Atomic Heart And THE FINAL closed beta.

The evolution of AI upscaling

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 the high-resolution versions. In order to be able to make these predictions with a high level of accuracy, a neural network model must be trained on countless images with different resolutions.

4K displays can pollute the visuals as lower resolution images need to be stretched to fit your screen. By using AI to upscale streamed video, it adjusts lower-resolution images with unmatched sharpness.

The deployed AI model can then capture low-resolution video, producing incredible sharpness and enhanced detail that no traditional scaler can replicate. Edges look sharper, hair looks more unkempt, and landscapes appear with striking clarity.

In 2019, an early version of this technology was released with SHIELD TV. It was a breakthrough that streamed content was optimized for TVs ranging primarily from 480p to 1080p and optimized for a 10ft viewing experience.

PC viewers typically sit much closer to their screens than TV viewers, requiring a higher level of processing and refinement for upscaling. With the GeForce RTX 40 and 30 series GPUs, users now have extremely powerful AI processors with Tensor cores that enable a new generation of AI upscaling through RTX VSR.

This is how RTX Video Super Resolution works

RTX VSR is a breakthrough in AI pixel processing that dramatically improves the quality of streamed video content beyond edge detection and feature sharpening.

Blocky compression artifacts are a persistent problem with streamed video. Whether the fault is with the server, the client, or the content itself, problems with traditional upscaling are often amplified, leaving a less than pleasant visual experience for those watching streamed content.

Click on the image to see the differences between bicubic upscaling (left) and RTX Video Super Resolution.

RTX VSR reduces or eliminates artifacts caused by compressing video – such as B. blocking, ringing artifacts at edges, washing out of high-frequency detail and banding in flat areas – while reducing lost textures. It also sharpens edges and details.

The technology uses a deep learning network that performs upscaling and reduction of compression artifacts in a single pass. The network analyzes the lower resolution video frame and predicts the target resolution residual image. This residual image is then overlaid on a conventional upscaled image, correcting artifacts and sharpening edges to match the output resolution.

The deep learning network is trained on a variety of content with different levels of compression. It learns about types of compression artifacts present in low-resolution or low-quality video that are otherwise absent in uncompressed images as a reference for network training. An extensive visual assessment is performed to ensure that the generated model is suitable for almost all real-world and gaming content.


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

The feature also requires an update to the latest GeForce Game Ready driver, available today, or the next NVIDIA Studio driver, which will be released in March. Both Chrome (version 110.0.5481.105 or higher) 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 Adjust Video Image Settings. Check the Super 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 improvement.

Learn more, including other setup configurations, in this NVIDIA Knowledge Base article.

Source link

Related Articles

Leave a Reply

Your email address will not be published. Required fields are marked *