Computer Science Thesis Oral

— 12:00pm

Location:
In Person and Virtual - ET - McWilliams Classroom, Gates Hillman 4303 and Zoom

Speaker:
DEVDEEP RAY , Ph.D. Candidate, Computer Science Department, Carnegie Mellon University
https://www.devdeepray.com/

Integrating Video Codec Design and Network Transport for Emerging Internet Video Streaming Applications

While the trade-offs between video quality, delay, and bandwidth utilization are clear cut for traditional video streaming applications (e.g. conferencing, video-on-demand), emerging Internet video streaming applications like social live video streaming (SLVS), and cloud gaming have unique properties and demanding QoE requirements that make choosing the right trade-off and achieving the desired QoE  challenging. Conventional video streaming systems combine techniques that have been developed independently in the field of video coding and network transport, which limits the achievable QoE for emerging video streaming applications.

In this thesis, we explore some techniques that take a holistic approach at designing video streaming systems that are tailored to the specific needs of emerging video streaming applications. We first present Vantage, a video streaming system designed to address the different QoE needs of real-time viewers and time-shifted viewers in SLVS applications. Second, we present two systems, Prism and ViXNN, for handling packet loss in the context of ultra-low latency applications like cloud gaming and remote-rendered AR/VR. Third, we discuss congestion control design for cloud gaming and cloud AR/VR, and present a tool, CC-Fuzz, for automated testing of new congestion control algorithms for emerging applications before they are deployed.

Thesis Committee:

Srinivasan Seshan (Chair)
Justine Sherry-Martins
Anthony Rowe David Chu (Magic Leap)

In Person and Zoom Participation. See announcement.

For More Information:
deb@cs.cmu.edu

Add event to Google
Add event to iCal