Machine-learning based high efficiency rate control for AV1

Yi CHEN, Yunhao MAO, Shiqi WANG, Xianguo ZHANG, Sam KWONG

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

1 Citation (Scopus)

Abstract

Recent years have witnessed the increasing demand of video coding technologies, which have been continuously developed to meet various requirements in video-related applications. Developed by Alliance for Open Media (AOM), the AOMedia Video 1 (AVl) is an open-source and royalty-free standard. Herein, we achieve high efficiency rate control for AVI based on the machine-learning model, which establishes the rate-quantization relationship in a data-driven manner. More specifically, the Supporting Vector Regression (SVR) is used for rate model parameter estimation. The model is trained using sufficient training data, and incorporated in the encoder. Compared to the default rate control scheme in AV 1, experimental results have shown that 2.01% bitrate could be saved with tolerable bitrate error.
Original languageEnglish
Title of host publicationProceedings of the 5th International Conference on Multimedia Information Processing and Retrieval
PublisherIEEE
Pages65-70
ISBN (Print)9781665495486
DOIs
Publication statusPublished - Aug 2022
Externally publishedYes
Event2022 IEEE 5th International Conference on Multimedia Information Processing and Retrieval - , United States
Duration: 2 Aug 20224 Aug 2022

Conference

Conference2022 IEEE 5th International Conference on Multimedia Information Processing and Retrieval
Country/TerritoryUnited States
Period2/08/224/08/22

Bibliographical note

This work was supported by the Hong Kong Innovation and Technology Commission (InnoHK Project CIMDA), Hong Kong RGC GRF Grant 9042816 (CityU 11209819) and Grant 9042958 (CityU 11203820), as well as the Tencent Rhino-Bird Fund.

Keywords

  • Quantization parameter (QP)
  • Rate control
  • Supporting vector regression
  • Video coding

Fingerprint

Dive into the research topics of 'Machine-learning based high efficiency rate control for AV1'. Together they form a unique fingerprint.

Cite this