Zoe was previously a software engineer with the Google Chrome Media team for 5 years, and has been a key contributor to the development and finalization of the open source video codec standard AOM/AV1.
Either as a principal contributor or as a Technical Lead, Zoe had once devoted her effort to the design and development of several renowned video call products, including Apple FaceTime, Tango Video Call, and Google Glass Video Call.
In this talk, we will introduce Aurora, our AV1 encoder optimized for both VoD and real-time communications use cases. We will share the updated results of Aurora for the use case of VoD as opposed to x264/x265, as well as other state-of-the-art AV1 open source encoders, w.r.t. their BD-Rate performance and encoder speed. We will include the newly collected results of Aurora and its great potential for real-time communications. We are currently tuning Aurora's fast speed level for its initial deployment for one online education platform. Bandwidth is very critical to such customer as they manage the teach/learn long-distance video conversations across the Pacific Ocean. Finally, we will introduce certain AI+codec techniques that could provide certain novel coding tools leveraging the use of deep learning for the next AOM standard, possibly AV2.