Fast CU partition decision using machine learning for screen content compression

Fanyi Duanmu, Zhan Ma, Yao Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Screen Content Coding (SCC) extension is currently being developed by Joint Collaborative Team on Video Coding (JCT-VC), as the final extension for the latest High-Efficiency Video Coding (HEVC) standard. It employs some new coding tools and algorithms (including palette coding mode, intra block copy mode, adaptive color transform, adaptive motion compensation precision, etc.), and outperforms HEVC by over 40% bitrate reduction on typical screen contents. However, enormous computational complexity is introduced on encoder primarily due to heavy optimization processing, especially rate distortion optimization (RDO) for Coding Unit (CU) partition decision and mode selection. This paper proposes a novel machine learning based approach for fast CU partition decision using features that describe CU statistics and sub-CU homogeneity. The proposed scheme is implemented as a 'preprocessing' module on top of the Screen Content Coding reference software (SCM-3.0). Compared with SCM-3.0, experimental results show that our scheme can achieve 36.8% complexity reduction on average with only 3.0% BD-rate increase over 11 JCT-VC testing sequences when encoded using 'All Intra' (AI) configuration.

Original languageEnglish (US)
Title of host publication2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings
PublisherIEEE Computer Society
Pages4972-4976
Number of pages5
Volume2015-December
ISBN (Print)9781479983391
DOIs
StatePublished - Dec 9 2015
EventIEEE International Conference on Image Processing, ICIP 2015 - Quebec City, Canada
Duration: Sep 27 2015Sep 30 2015

Other

OtherIEEE International Conference on Image Processing, ICIP 2015
CountryCanada
CityQuebec City
Period9/27/159/30/15

Fingerprint

Image coding
Learning systems
Motion compensation
Computational complexity
Statistics
Color
Testing
Processing

Keywords

  • HEVC
  • Machine Learning
  • Neural Network
  • Partition Decision
  • Screen Content Coding

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Duanmu, F., Ma, Z., & Wang, Y. (2015). Fast CU partition decision using machine learning for screen content compression. In 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings (Vol. 2015-December, pp. 4972-4976). [7351753] IEEE Computer Society. https://doi.org/10.1109/ICIP.2015.7351753

Fast CU partition decision using machine learning for screen content compression. / Duanmu, Fanyi; Ma, Zhan; Wang, Yao.

2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings. Vol. 2015-December IEEE Computer Society, 2015. p. 4972-4976 7351753.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Duanmu, F, Ma, Z & Wang, Y 2015, Fast CU partition decision using machine learning for screen content compression. in 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings. vol. 2015-December, 7351753, IEEE Computer Society, pp. 4972-4976, IEEE International Conference on Image Processing, ICIP 2015, Quebec City, Canada, 9/27/15. https://doi.org/10.1109/ICIP.2015.7351753
Duanmu F, Ma Z, Wang Y. Fast CU partition decision using machine learning for screen content compression. In 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings. Vol. 2015-December. IEEE Computer Society. 2015. p. 4972-4976. 7351753 https://doi.org/10.1109/ICIP.2015.7351753
Duanmu, Fanyi ; Ma, Zhan ; Wang, Yao. / Fast CU partition decision using machine learning for screen content compression. 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings. Vol. 2015-December IEEE Computer Society, 2015. pp. 4972-4976
@inproceedings{f221580e9d1a4f7fa3cb7bc94cc5166f,
title = "Fast CU partition decision using machine learning for screen content compression",
abstract = "Screen Content Coding (SCC) extension is currently being developed by Joint Collaborative Team on Video Coding (JCT-VC), as the final extension for the latest High-Efficiency Video Coding (HEVC) standard. It employs some new coding tools and algorithms (including palette coding mode, intra block copy mode, adaptive color transform, adaptive motion compensation precision, etc.), and outperforms HEVC by over 40{\%} bitrate reduction on typical screen contents. However, enormous computational complexity is introduced on encoder primarily due to heavy optimization processing, especially rate distortion optimization (RDO) for Coding Unit (CU) partition decision and mode selection. This paper proposes a novel machine learning based approach for fast CU partition decision using features that describe CU statistics and sub-CU homogeneity. The proposed scheme is implemented as a 'preprocessing' module on top of the Screen Content Coding reference software (SCM-3.0). Compared with SCM-3.0, experimental results show that our scheme can achieve 36.8{\%} complexity reduction on average with only 3.0{\%} BD-rate increase over 11 JCT-VC testing sequences when encoded using 'All Intra' (AI) configuration.",
keywords = "HEVC, Machine Learning, Neural Network, Partition Decision, Screen Content Coding",
author = "Fanyi Duanmu and Zhan Ma and Yao Wang",
year = "2015",
month = "12",
day = "9",
doi = "10.1109/ICIP.2015.7351753",
language = "English (US)",
isbn = "9781479983391",
volume = "2015-December",
pages = "4972--4976",
booktitle = "2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Fast CU partition decision using machine learning for screen content compression

AU - Duanmu, Fanyi

AU - Ma, Zhan

AU - Wang, Yao

PY - 2015/12/9

Y1 - 2015/12/9

N2 - Screen Content Coding (SCC) extension is currently being developed by Joint Collaborative Team on Video Coding (JCT-VC), as the final extension for the latest High-Efficiency Video Coding (HEVC) standard. It employs some new coding tools and algorithms (including palette coding mode, intra block copy mode, adaptive color transform, adaptive motion compensation precision, etc.), and outperforms HEVC by over 40% bitrate reduction on typical screen contents. However, enormous computational complexity is introduced on encoder primarily due to heavy optimization processing, especially rate distortion optimization (RDO) for Coding Unit (CU) partition decision and mode selection. This paper proposes a novel machine learning based approach for fast CU partition decision using features that describe CU statistics and sub-CU homogeneity. The proposed scheme is implemented as a 'preprocessing' module on top of the Screen Content Coding reference software (SCM-3.0). Compared with SCM-3.0, experimental results show that our scheme can achieve 36.8% complexity reduction on average with only 3.0% BD-rate increase over 11 JCT-VC testing sequences when encoded using 'All Intra' (AI) configuration.

AB - Screen Content Coding (SCC) extension is currently being developed by Joint Collaborative Team on Video Coding (JCT-VC), as the final extension for the latest High-Efficiency Video Coding (HEVC) standard. It employs some new coding tools and algorithms (including palette coding mode, intra block copy mode, adaptive color transform, adaptive motion compensation precision, etc.), and outperforms HEVC by over 40% bitrate reduction on typical screen contents. However, enormous computational complexity is introduced on encoder primarily due to heavy optimization processing, especially rate distortion optimization (RDO) for Coding Unit (CU) partition decision and mode selection. This paper proposes a novel machine learning based approach for fast CU partition decision using features that describe CU statistics and sub-CU homogeneity. The proposed scheme is implemented as a 'preprocessing' module on top of the Screen Content Coding reference software (SCM-3.0). Compared with SCM-3.0, experimental results show that our scheme can achieve 36.8% complexity reduction on average with only 3.0% BD-rate increase over 11 JCT-VC testing sequences when encoded using 'All Intra' (AI) configuration.

KW - HEVC

KW - Machine Learning

KW - Neural Network

KW - Partition Decision

KW - Screen Content Coding

UR - http://www.scopus.com/inward/record.url?scp=84956623230&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84956623230&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2015.7351753

DO - 10.1109/ICIP.2015.7351753

M3 - Conference contribution

SN - 9781479983391

VL - 2015-December

SP - 4972

EP - 4976

BT - 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings

PB - IEEE Computer Society

ER -