AI4Media@AI4EU Café: Video Compression turns to Artificial Intelligence

Abstract:

Artificial Intelligence (AI) technologies are used in more and more applications yielding one of the fastest growing research in data analysis. Their usage can now be found in wide range of applications, including Image Processing, Image Enhancement and, recently, Video Coding. Users demand high resolutions, wide range of colors and richer details under bandwidth constraint. For this purpose, current state of the art image and video compression algorithms (e.g. High Efficiency Video Coding - HEVC - and its successor Versatile Video Coding - VVC) have some limitations: they are agnostic to the semantics of data being compressed as they work at low level (i.e., pixel level), and they perform exhaustive search for rate-distortion optimization. In order to produce more accurate and visually pleasing pictures at much higher compression levels, new generations of AI-empowered compression standards are needed.