Media production is facing tremendous challenges during processing and transmission, due to large data volume, high computational complexity and real-time transmission requirement. Hence, more and more media servers tend to spread media content in a distributed manner, over e.g., cloud platform or edge computing nodes, which are closer to client side and/or have adequate computing capacity. Benefiting from cloud or edge computing, users can receive various media service with high quality and low latency. Network-based Media Processing (NBMP) established by International Organization for Standardization (ISO)/International Electrotechnical Commission (IEC) standard organization-Moving Picture Experts Group (MPEG), is one of these representative distributed architectures, which has attracted a wide range of attention. This paper focuses on emerging cloud and edge computation for media production to highlight the necessity of adopting a distributed computing framework. We take NBMP architecture as an example, and introduce the basic components and workflow in distributed processing frameworks. Moreover, we also provide related application instances based on NBMP with the hope of promoting future development of cloud and edge computation.

中文翻译：

---

使用云和边缘计算的媒体制作：最新进展和基于 NBMP 的实施


由于数据量大、计算复杂度高、实时传输要求高，媒体制作在处理和传输过程中面临着巨大的挑战。因此，越来越多的媒体服务器倾向于通过例如更靠近客户端和/或具有足够计算能力的云平台或边缘计算节点以分布式方式传播媒体内容。受益于云或边缘计算，用户可以接收高质量、低延迟的各种媒体服务。国际标准化组织（ISO）/国际电工委员会（IEC）标准组织——运动图像专家组（MPEG）建立的基于网络的媒体处理（NBMP）就是其中具有代表性的分布式架构之一，吸引了广泛的关注。注意力。本文重点关注媒体制作中新兴的云计算和边缘计算，以强调采用分布式计算框架的必要性。我们以NBMP架构为例，介绍分布式处理框架的基本组件和工作流程。此外，我们还提供了基于NBMP的相关应用实例，希望能够推动云计算和边缘计算未来的发展。