iSize Develops AI-Based ‘Precoder’

iSize Technologies’ BitSave v.2 is described as a pixel-to-pixel neural-network solution that optimizes video frames before the pixels reach the video compression software.

This ‘precoder’ is said to enhance details of the areas of each frame that affect the perceptual quality score of the content after encoding and attenuates details that are not important.

This, says iSize, is designed to optimally balance perceptual quality against encoding bitrate. The solution is data-driven, trained on large image and video datasets, with no hand-crafted parameters.

It incurs a single-frame latency, can be used with any third-party video encoder with no changes in the encoding pipeline, and can run in real-time for up to 4K resolution.

iSize Technologies CEO Sergio Grce said, “It is predicted that by the end of 2020, more than 82% of internet traffic will be taken up by video, with consumers increasingly investing in and consuming higher quality video content. In response to this fast-moving market, iSize develops innovative codec independent software solutions that allows data-heavy video content to be compressed to a fraction of its original size, meaning content can be streamed faster and at a better quality.”

Extensive testing has shown its patent-pending AI features can make encoding up to 500% faster.

Since BitSave can be used alongside existing software, companies that have invested in compression software can use BitSave as an ‘add-on’ without having to shelve ongoing projects. The AI technology behind BitSave is fully codec independent, increasing the efficiency and performance of all the latest codec standards including AVC/H.264, HEVC/H.265, and VP9. This ensures seamless integration with existing media workflows.

BitSave is also unconstrained by standards because it produces a pixel output, which means it can use neural networks and add multiple quality functions that cannot be achieved otherwise.

“Ultimately, BitSave allows consumers to stream higher quality video, using less data or bandwidth, thus reducing the environmental impact of streaming. The devices used will also need to use less computing power to stream quality video, which means a longer battery life when watching content on the go,” says Grce.

You might also like...

Software-Defined Automation: Are We Nearly There Yet? Part II

Playout automation has been enabling fewer people to control more channels for decades but we’re not quite at the point where human interaction can be eliminated altogether. Since most linear broadcasters will either move to a software-based deployment for t…

VSF RIST Spec On Road To Wide Implementation

In 2017, at that year’s VidTrans conference a regional gathering of members of the Video Services Forum (VSF), a new protocol for delivering audio and video over lossy IP networks (including the public Internet), was born. It was an idea t…

The Sponsors Perspective: Reaching OTT At Scale - Pitfalls And Opportunities

OTT delivery continues to expand to meet the relentless growing consumer demand. This trend shows no chance of abating and technologists are continually looking to innovation to scale infrastructures accordingly. In this sponsors perspective, Ryan Nicometo, SVP of Product for…

The New Era Of Broadcast - Mezzanine Links And Beyond

20 years ago, broadcast television went through an evolution as it transitioned from analog to digital distribution. This migration was driven by the demand for larger channel counts and spectrum reallocation. Since that transition, another, even more significant sea change has…

Core Insights - Operating An IP Broadcast Facility

Whether we’re routing signals or remotely operating equipment, the need for reliable system control is one of the most important aspects of a broadcast facility. But as we migrate to IP, some of the working practices we took for g…