Efficient screen content intra coding based on statistical learning

作者：

Highlights：

•

• An efficient intra coding algorithm is proposed based on three kinds of features, including texture information, coding information of spatial nearby coded CUs and current CU.

• One classifier is designed to determine whether current CU should be directly split into four sub-CUs or not.

• One classifier is designed to decide either 35 traditional intra modes or SCC modes (i.e. intra block copy mode and palette mode) will be performed at current CU depth level.

摘要

•An efficient intra coding algorithm is proposed based on three kinds of features, including texture information, coding information of spatial nearby coded CUs and current CU.•One classifier is designed to determine whether current CU should be directly split into four sub-CUs or not.•One classifier is designed to decide either 35 traditional intra modes or SCC modes (i.e. intra block copy mode and palette mode) will be performed at current CU depth level.

论文关键词：Screen content coding,Intra prediction,Fast algorithm,Statistical learning

论文评审过程：Received 2 June 2017, Revised 16 October 2017, Accepted 1 December 2017, Available online 14 December 2017, Version of Record 30 December 2017.

论文官网地址：https://doi.org/10.1016/j.image.2017.12.001