NVIDIA's AI Utilization to Enhance Video Streaming Quality

Jakarta, INTI - Video is everywhere – nearly 80% of today's internet bandwidth is used for streaming video from various content providers and social networks. While screens are getting larger and supporting higher resolutions, most videos are still of 1080p quality or lower.

Upscalers can help sharpen streaming videos, and with AI support on the NVIDIA RTX platform, they can significantly enhance the image quality and detail.

What is an Upscaler?

Larger video file sizes make them harder to compress and transmit compared to images or text. Platforms like Netflix, Vimeo, and YouTube address this limitation by encoding videos – the process of compressing raw video sources into smaller container formats.

Encoders first analyze the video to decide what information can be removed to fit the target resolution and frame rate. If the target bitrate is insufficient, video quality degrades, resulting in loss of detail and sharpness and the presence of encoding artifacts. The smaller the file, the easier it is to share on the internet – but the worse it looks.

Typically, software on the viewer's device will upscale the video file to fit the screen's native resolution. However, these upscalers are quite basic, merely multiplying pixels to meet the desired resolution. They can help sharpen object outlines and scenes, but the final video usually carries encoding artifacts and sometimes looks overly sharp and unnatural.

AI Offers a Better Way

The NVIDIA RTX platform uses AI to easily remove artifacts and upscale videos.

The AI upscaling process involves analyzing images and motion vectors to generate new details not present in the original video. Instead of just multiplying pixels, AI recognizes image patterns and enhances them to provide greater detail and video quality.

Images must first be de-artifacted before processing begins. Artifacts – unwanted distortions and anomalies that appear in video and image files – occur due to over-compression or data loss during transmission and storage.

NVIDIA's AI networks can remove image artifacts, helping eliminate the blocky areas sometimes seen in streaming videos. Without this first step, AI upscaling might end up enhancing the artifacts themselves instead of the desired content.

Super-Sized Video

Just like wearing prescription glasses that can instantly bring the world into focus, RTX Video Super Resolution, one of NVIDIA's latest innovations in AI-enhanced video technology, gives users a clearer view of the streaming video world.

Available on GeForce RTX 40 and 30 Series GPUs and RTX professional GPUs, it uses AI running on dedicated Tensor Cores to remove block compression artifacts and upscale low-resolution content up to 4K, matching the user's display's native resolution.

RTX Video Super Resolution can be used to enhance all videos watched in a browser. By combining de-artifacting with AI upscaling techniques, it can make low-bitrate Twitch streams look incredibly clear. RTX Video Super Resolution is also supported in popular video applications like VLC, allowing users to apply the same enhancement process to offline videos.

Content creators can soon utilize RTX Video Super Resolution in editing applications like Black Magic's Davinci Resolve, making it easier than ever to upscale low-quality video files to 4K resolution and convert standard dynamic range (SDR) source files to high dynamic range (HDR).

Say Hello to High Dynamic Range

RTX Video now also supports AI HDR. HDR video supports a wider range of colors, providing greater detail especially for darker and brighter areas of an image. The problem is there isn't much HDR content online yet.

Enter RTX Video HDR – by simply enabling this feature, the AI network will convert standard or low dynamic range content to HDR, performing correct tone mapping so that images look natural and retain their original colors.

AI Across the Board

RTX Video is just the latest implementation of AI-enhanced upscaling powered by NVIDIA RTX.

Members of the GeForce NOW cloud streaming service can play their favorite PC games on almost any device. GeForce RTX servers located worldwide first render the game content, encode it, and then stream it to the player's local device – just like streaming video from any other content provider.

Members on devices supported by older NVIDIA GPUs can still use AI-enhanced upscaling to improve gameplay quality. This means they can enjoy the best of both worlds – gameplay rendered on servers powered by RTX 4080-class GPUs in the cloud and AI-enhanced streaming quality. Learn more about enabling AI-enhanced upscaling on GeForce NOW.

NVIDIA SHIELD TV takes it a step further, processing AI neural networks directly on the NVIDIA Tegra system-on-a-chip to upscale 1080p or lower content from almost any streaming platform to the display's native resolution. This means users can improve the video quality of content streamed from Netflix, Prime Video, Max, Disney+, and more with the press of a remote button.

SHIELD TV is currently available with up to $30 off in North America and £30 or €35 off in Europe as part of Amazon's Prime Day event running from July 16-17. For Prime members in Europe, qualifying SHIELD TV purchases also include one month of GeForce NOW Ultimate membership for free, enabling GeForce RTX 4080-class PC gameplay streamed directly to the living room.

AI has enabled unprecedented improvements in video quality, helping to set a new standard in streaming experiences.

Invitation to Indonesia Technology and Innovation 2024

Don't miss the opportunity to attend Indonesia's largest technology and innovation exhibition, Indonesia Technology and Innovation 2024 (INTI 2024), which will be held at JI-EXPO on August 12-14, 2024. For more information, visit https://inti.asia/.