Central South University
Dr. Zhang, Hao, currently a professor at Computer School of Central South University, obtained his MA in Statistics from Columbia University and Ph.D from Polytechnic University in New York(currently NYU Tandon School of Engineering). He was awarded IEE Swan Premium Award and Second-place Prize of Ministry of Education of the People Republican of China. Since 2006, Dr. Zhang worked at Vidyo on H.264/SVC. After returning back, he cooperated with many well-known companies on video technologies and achieved satisfactory outcome.
Track: Video Codec
2019/04/20 09:30 - 17:55
Video Codec is the field that relatively mature but rapid development constantly, new standard of video codec is endless, and new technology application is also changing quickly, the result of these factors is to inject young blood and energy into traditional field constantly, and it means that the engineers and researchers from the field need to learn new technology and develop new algorithm for meeting updated standard.2019 is important year for video codec, VVC standard is expected to be completed before long, more and more companies will invest in VVC that is being productized，the optimization and productization of AV1 and AVS3 will bring new scenery for industry. In addition, the devices with HDR screen and powerful GPU will become popular, and will also promote the popularization of a set of related technology and application.
Topics in the track
The international standard organization MPEG and VCEG jointly launched the technical solution development of the new generation video coding standard VVC (Versatile Video Coding) in April 2018. Starting from the stage of Call for Proposal, VVC has been aiming at three major applications of ultra-high definition video, HDR video and 360 panoramic video, to explore innovative technologies. In the scheme design, VVC follows the traditional block-based hybrid coding architecture, and developed a number of innovative technologies in different modules including block partition, intra-frame and inter-frame prediction, transform, quantization, and entropy coding, which significantly improve compression efficiency. In addition, functionalities such as reference picture management and sub-picture parallel processing are improved and enhanced, which enables better encoder flexibility and more efficiently processing of large-resolution pictures. Work on the planned VVC standard will end in October 2020, and all experts in the standard committee will continue to optimize existing solutions based on industry feedback in the next 18 months.
The main content of National standard of video coding and its latest development is to elaborate the evolution of AVS video coding standard and the current development and key coding technologies of the new generation video coding standard AVS3. It will help the researchers to further understand AVS and advanced video coding technologies. It is also benefit to improve the understanding of video coding technologies.
TPG is a picture compression format developed by Tencent Media Lab. In this talk, we will introduce the development process of TPG. we will also introduce our recent work on screen content coding and its application in wireless projection.
This paper analyzes the characteristics and challenges of real-time cloud video communication, and introduces the video coding technology in real-time cloud video communication. This paper mainly introduces the architecture and coding technology of screen content video sharing. It is suitable for listeners interested in real-time cloud video communication and screen content sharing to help them understand the difficulties and solutions of real-time cloud video communication and desktop content sharing.
Video Encoder is the key component of video cloud. It could run on different platforms. However, there are pros and cons on compression ratio, performance and cost for a single platform. The optimal solution could be achieved by combining different platforms into a heterogeneous one and utilizes all the advantages by encoder algorithms.
This talk presents one learning-based scheme for selecting optimal rate-control parameters in video encoding. Firstly, we will propose an automatic labeling method for optimal rate-control parameters. Then, we will propose the end-to-end deep learning method for learning the optimal rate control for each video shot. Experiments will show our scheme can save bitrates remarkably compared with the one using fixed rate-control parameters.