多样化的网络视频消费近几年呈井喷趋势增长，视频编码是其背后的关键技术推手，深度影响了包括视频直播、短视频分享、视频会议、视频安防监控、远程医疗、在线教育、网络游戏、视频广播、视频云服务等视频消费的多种行业。

 

AV1是最新推出的开源和无版税的视频压缩标准，由开放媒体联盟（AOM）在2018年初开发完成。 AOM由世界顶尖技术的高科技公司加盟，目前在全球拥有35名成员。AOM的使命是成员间协同合作，推出更高效、更节约成本、质量更卓越的视频技术。 AV1的目标是通过最先进的视频编解码标准，实现大幅度的视频压缩增益，同时保持实用的解码复杂度和硬件可行性。

 

本次演讲会首先对AOM做简要介绍，同时简单回顾AV1的前身VP9压缩标准在YouTube上的成功应用。演讲会主要对AV1中所涉及的关键编码工具做简要概述，包括变换编码工具、预测编码工具、环路内滤波工具以及其他关键技术，最后会给出AV1在压缩性能上与VP9和HEVC标准的比对结果。

 

Abstract:

 

Video coding has served as the key technology that drives the recent explosive growth of online video consumption, covering a broad variety of industries including live video streaming, short video sharing, video conferencing, video surveillance, remote medicine, online education, online gaming, video broadcasting, cloud video services, etc.

 

AV1 is an emerging open-source and royalty-free video compression format, which is jointly developed and finalized in early 2018 by the Alliance for Open Media (AOM) industry consortium. AOM unites top tech leaders behind a collaborative effort and now comprises 35 members worldwide, targeted to make video technology more efficient, cost-effective, and of superior quality. The main goal of AV1 is to achieve substantial compression gains over state-of-the-art video codecs while maintaining practical decoding complexity and hardware feasibility.

 

This talk will include a brief introduction of AOM, a short overview of the successful deployment of VP9 - the predecessor of AV1 in YouTube, and then the technical overview of the key coding techniques in AV1. The transform coding tools, the prediction coding tools, the in-loop filtering tools, and all other key techniques that have been incorporated in AV1 will be covered. This talk will draw its conclusion with the compression performance of AV1 in comparison against both VP9 and HEVC.

 

 

 

刘宇新于1990年至2000年就读于清华大学自动化系，1995年获工学学士学位，并获得校级优秀毕业生称号，2000年作为直博生获工学博士学位，师从中科院院士、著名信号处理与生物信息学专家李衍达教授。同年入学普渡大学，于2004年获第二个工学博士学位，师从著名图像处理、视频编码、信息安全与密码学专家Edward Delp教授。她是开放媒体联盟（AOM）新一代开源视频编解码标准AV1的主要贡献者，对图像/视频编码标准及相应编解码器优化技术拥有深入的研发经验。她是多个拥有数亿活跃用户或变革性视频通话产品研发团队的核心成员，包括苹果公司的FaceTime、谈客视讯的多移动平台视频通话APP、以及谷歌眼镜的视频通话APP。她拥有多个世界著名研究实验室的工作经验，包括贝尔实验室、诺基亚研究中心、太阳微处理器中心实验室、以及惠普实验室。她尤其擅长跨领域、跨学科、跨地域的研究与开发合作，已发表40篇国际会议/期刊论文，署名50多项正在审定或已授权的技术专利。她被推选为2018年谷歌开发者大会（Google I/O）发言人，面向全球开发者介绍AV1的背景技术以及应用前景。她的主要研究兴趣领域包括视频压缩、处理、传输、分析与理解等。

 

Speaker's Bio:

 

Zoe Liu (zoeliu@google.com) is a software engineer with Google's Chrome WebM team and has been a key contributor to the open source video codec standard AOM/AV1 (http://aomedia.org/). Zoe received her PhD/ME/BE from the Department of Automation, Tsinghua University, under the supervision of Prof Yanda Li, a world-renowned expert in the field of Signal Processing and Bioinformatics, and a member of the Chinese Academy of Sciences. Zoe earned her second PhD from Purdue University, under the supervision of Prof Edward Delp, a world-renowned expert in the field of Image Processing, Video Compression, and Cryptography, and an IEEE Fellow, a SPIE fellow, an IS&T Fellow, and a Fellow of the American Institute of Medical and Biological Engineering. Either as a principal contributor or as a Technical Lead, Zoe had previously devoted her effort to the design and development of several renowned video call products, including Apple's FaceTime, Tango Video Call, and Google Glass Video Call. Zoe has been one of the key contributors to the development and finalization of AV1. Zoe has accumulated years of innovative research experiences at prestigious research labs, including Bell Labs, Nokia Research Center, Sun Labs, and HP Labs, and in particular excels in cross-field effort. Zoe has published 40 international conference and journal papers, and filed over 50 patents worldwide. She has been selected as a 2018 Google I/O speaker to introduce AV1 to the worldwide developers. Her main research interests include video compression, processing, communications, analysis and understanding.

 

 

联系人：季向阳