AI-Cafe presents: Video Compression turns to Artificial Intelligence

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 a wide range of applications, including Image Processing, Image Enhancement and, recently, Video Coding. Users demand high resolutions, a wide range of colors and richer details under bandwidth constraints.

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) has 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 an 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.