Ioannis of Meta Platforms

We will review the history of video encoding, covering aspects of video codecs and quality metrics that have been exploited to optimize video delivery. Next, we will discuss the roots of convex optimization in video coding, connecting statistical multiplexing, rate-distortion optimization and how these led to the dynamic optimization framework. We will also discuss the complexity of video encoding (and quality metrics) and present the concept of a three-part tradeoff among bitrate-quality-complexity, as well as the important role this tradeoff plays in massive video processing systems. We will analyze software (SW) and hardware (HW) transcoding pipelines and conclude with an array of open research problems, including the use of ML/AI in video coding and video quality metrics.

Biography:

Dr. Ioannis Katsavounidis (Fellow IEEE) is part of the Media Foundation team, leading technical efforts to improve video quality and quality of experience across all video products at Meta. He received a Technical Emmy for the Meta Scalable Video Processor (MSVP) in 2024. He worked 3.5 years at Netflix, contributing to the development and popularization of VMAF, Netflix's open-source video quality metric and the Dynamic Optimizer video quality optimization framework, earning Netflix two technical Emmys in 2020. He was a professor for 8 years at the University of Thessaly's ECE Department in Greece. He was a co-founder of Cidana, a startup in Shanghai, China. He was director of software at InterVideo, in the early 2000's and he worked 4 years in experimental Physics in Italy. He is general co-chair of the Video Quality Experts Group (VQEG). He is co-chair of the software implementation working group (SWIG) in the Alliance for Open Media (AOM). He has over 200 publications, including 60+ patents. His research interests lie in video coding, quality of experience, adaptive streaming, and energy-efficient HW/SW multimedia processing.