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 Coding & Decoding Standard and Optimization
2019/12/14 09:30 - 17:55
Topics in the track
This sharing will mainly focus on introducing overview of image and video quality enhancements, difficulties in real-time video quality enhancement, ROI coding based on visual saliency, decode combined real-time video super resolution, and how to apply heterogeneous accelerated video enhancement on mobile device and outlook of mobile video processing in the 5G era
With the advent of 5G era, multimedia technology has entered the era of 4K/8K ultra-high definition video. In order to cope with the real-time transmission technology challenges brought by the explosion of ultra-high definition video data flux and the security challenges of the codec kernel supply chain, the China Audio and Video Codec Standards Working Group has formulated national standards for 4K and 8K respectively, and has promoted them internationally. This report focuses on AVS series standard technology for next generation video applications and the application ecology construction in the fields of radio and television, IPTV, and mobile Internet.
There has been an incredible growing interest in recent years in the development of perceptual video coding algorithms that improves the ultimate user experience. In this talk, we will show how the coding performance in terms of perceptual quality could be improved in the full chain of video coding and processing. Moreover, we will also discuss the challenges that would hamper the wide usage of such algorithms in real-world applications. Finally, the future video codec optimization techniques and trends that aim to improve the coding performance in terms of perceptual quality will also be envisioned. The potential audience include but not limited to the researchers/developers in video coding, processing and quality assessment.
The rapid growth of cloud video applications makes us need more efficient video codecs to meet diverse transcoding requirements. Using scalable video technology (SVT), the encoder can achieve the highest degree of parallelism while achieving the best tradeoff between coding quality and speed. This report describes the architecture of SVT, introduces the efficient coding tools in AVS3 and the optimization results of SVT-AVS3 encoder.
Last year, the Alliance for Open Media released its next-generation video codec AV1. It achieves better compression than proprietary competitors, while its patents can be licensed via a royalty-free, open-source friendly license. With a broad array of industry support including all major browser vendors, many hardware partners, internet streaming and video conferencing providers, we think this is our best chance yet to create a successful video codec that achieves wide deployment. However publishing the AV1 standard is just the first step towards broad adoption. Now that the bitstream is finalized research has shifted to encoder algorithms for use in real-world, production environments. The Rust AV1 Encoder (rav1e) project at Mozilla is a clean room AV1 implementation targeting a variety of operating points. Where the standardization effort focused on tools that improved objective metrics, the rav1e project is focused on algorithms that improve perceived video quality.
Wake up the super high definition video application in 5G era——KingSoft Smart High Definition and AV1 encoder
With the coming of 5G era, the quantity of video data will increase explosively, making the research on the cloud transcoding technologies of great strategic significance. Kingsoft Cloud has been working in the field of video cloud transcoding for many years, and has developed industry-leading video coding products like KSC265 and Kingsoft Smart High Definition (KSHD). With these accumulated technologies, Kingsoft Cloud is currently promoting the application of AV1, the new generation of video coding technology. AV1 was finalized in June 2018, which can achieve higher compression ratio than H. 265 with good ecology. This talk will share how Kingsoft Cloud customizes AV1 optimization strategies for cloud transcoding scenarios.