MPAI-EEV: Standardization Efforts of Artificial Intelligence based End-to-End Video Coding

TL;DR

This paper discusses the development of the MPAI-EEV standard for AI-based end-to-end neural video coding, emphasizing improved compression efficiency and applications like UAV video, with promising results over traditional standards.

Contribution

It introduces the MPAI-EEV standard, highlighting its design philosophy, key technologies, and performance advantages over existing standards like H.266/VVC.

Findings

EEV model outperforms H.266/VVC in perceptual quality

Standardization efforts include UAV video coding applications

The approach leverages neural networks for efficient high-fidelity video compression

Abstract

The rapid advancement of artificial intelligence (AI) technology has led to the prioritization of standardizing the processing, coding, and transmission of video using neural networks. To address this priority area, the Moving Picture, Audio, and Data Coding by Artificial Intelligence (MPAI) group is developing a suite of standards called MPAI-EEV for "end-to-end optimized neural video coding." The aim of this AI-based video standard project is to compress the number of bits required to represent high-fidelity video data by utilizing data-trained neural coding technologies. This approach is not constrained by how data coding has traditionally been applied in the context of a hybrid framework. This paper presents an overview of recent and ongoing standardization efforts in this area and highlights the key technologies and design philosophy of EEV. It also provides a comparison and report on some primary efforts such as the coding efficiency of the reference model. Additionally, it discusses emerging activities such as learned Unmanned-Aerial-Vehicles (UAVs) video coding which are currently planned, under development, or in the exploration phase. With a focus on UAV video signals, this paper addresses the current status of these preliminary efforts. It also indicates development timelines, summarizes the main technical details, and provides pointers to further points of reference. The exploration experiment shows that the EEV model performs better than the state-of-the-art video coding standard H.266/VVC in terms of perceptual evaluation metric.