AI-Based Media Coding Standards

Authors: Basso Andrea; Ribeca Paolo; Bosi Marina; Pretto Niccolo; Chollet Gerard; Guarise Michelangelo; Choi Miran; Chiariglione Leonardo; Iacoviello Roberto; Banterle Franesco; Artusi Alessandro; Gissi Francesco; Fiandrotti Attilio; Ballocca Giovanni; Mazzaglia Marco; Moskowitz Scott

Journal: 40077

Publisher: Society of Motion Picture and Television Engineers

Published: 2022

DOI: 10.5594/JMI.2022.3160793

Volume: 131, Issue: 4, Pages: 10-20

Keywords: Artificial Intelligence (AI); Audio enhancement; IP license; Standards; Video compression;

Research Topics: Coding (social sciences); Computer science; Engineering; Artificial intelligence; Mathematics

Citations: 6 (source: OpenAlex)

Abstract

Moving Picture, Audio and Data Coding by Artificial Intelligence (MPAI) is the first standards organization to develop data coding standards that have artificial intelligence (AI) as their core technology. MPAI believes that universally accessible standards for AI-based data coding can have the same positive effects on AI as standards had on digital media. Elementary components of MPAI standards-AI modules (AIMs)-expose standard interfaces for operation in a standard AI framework (AIF). As their performance may depend on the technologies used, MPAI expects that competing developers providing AIMs will promote horizontal markets of AI solutions that build on and further promote AI innovation. Finally, the MPAI framework licences (FWLs) provide guidelines to intellectual property right (IPR) holders facilitating the availability of compatible licenses to standard users.