AI-based Multimedia Data Compression: Perception Utility Optimization and Standardization

摘要

Different 2D and 3D visual data have been widely used in applications such as UHDTV, mobile phones, autonomous driving, robots, and UAVs, etc. The large-scale data amount has raised the research and development trends of image and video coding, and point cloud coding. Compression technologies can efficiently reliever the burden of communication and storage. This tutorial will discuss diverse aspects of multimedia data compression, including datasets, perception models, deep learning-based coding methods, AI-based standards, open source projects, and future research.