Enhanced intra prediction with recurrent neural network in video coding

Yueyu Hu, Wenhan Yang, Sifeng Xia, Wen-Huang Cheng, Jiaying Liu*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

16 Scopus citations

Abstract

Intra prediction is one of the important parts in video/image codec. With intra prediction mechanism, spatial redundancy can be largely removed for further bit saving. However, current state-of-the-art intra prediction method does not produce satisfactory prediction result due to its limits in reference samples and modeling ability. To enhance the intra prediction in HEVC, in this paper, a deep neural network featuring spatial RNN, which models the spatial dependency of pixels as sequential dynamics, is proposed to generate better prediction signals. Experimental results show improvement in BD-Rate for the proposed method compared with the original HEVC prediction scheme.

Original languageEnglish
Title of host publicationProceedings - DCC 2018
Subtitle of host publication2018 Data Compression Conference
EditorsAli Bilgin, James A. Storer, Joan Serra-Sagrista, Michael W. Marcellin
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages1
ISBN (Electronic)9781538648834
DOIs
StatePublished - 19 Jul 2018
Event2018 Data Compression Conference, DCC 2018 - Snowbird, United States
Duration: 27 Mar 201830 Mar 2018

Publication series

NameData Compression Conference Proceedings
Volume2018-March
ISSN (Print)1068-0314

Conference

Conference2018 Data Compression Conference, DCC 2018
CountryUnited States
CitySnowbird
Period27/03/1830/03/18

Keywords

  • HEVC
  • Intra Prediction
  • Recurrent Neural Network
  • Video Coding

Fingerprint Dive into the research topics of 'Enhanced intra prediction with recurrent neural network in video coding'. Together they form a unique fingerprint.

Cite this