Machine Learning Based UHD Up-conversion Using Generative Neural Networks

Ultra HD (UHD) is now part of mainstream TV production. Various consumer electronic companies now offer a wide range of high-quality UHD TV sets, which accounts for a significant proportion of all new TVs sold globally. The popularity of UHD has raised viewers’ expectations for a stunning quality experience. In today’s media landscape, online providers have moved quickly to satisfy this UHD demand via ABR delivery.

However, there remains a limited amount of content available that is UHD-native, and traditional content providers have a wealth of great content to offer the consumers even more value in UHD format. As consumer expectations grow, broadcasters will need to provide higher quality experiences, moving from a few UHD events to full-time or pop up channels, even if this is delivered only over ABR infrastructure. The question about where to get valuable UHD content remains open-ended, even though traditional up-conversion techniques can result in an end user experience that is more “HD-like”?than UHD.

This presentation explores a different approach to up-conversion, using Generative Adversarial Neural Networks to synthesize detail in the upconverted image, leading to an experience that is much closer to native UHD, leading to more compelling, higher quality experiences for consumers.

Alex Okell | MediaKind | Hedge End, Hampshire, United Kingdom
Tony Jones | MediaKind | Hedge End, Hampshire, United Kingdom