Machine Learning-Based Early Skip Decision for Intra Subpartition Prediction in VVC
The recently published video coding standard, Versatile Video Coding (VVC/H.266), has the intra subpartition (ISP) coding mode, which divides an intra-predicted block into smaller blocks called subpartitions, each of which can be predicted using the newly reconstructed subpartition while still shari...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2022-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9921285/ |
_version_ | 1811234333647699968 |
---|---|
author | Jeeyoon Park Bumyoon Kim Jeehwan Lee Byeungwoo Jeon |
author_facet | Jeeyoon Park Bumyoon Kim Jeehwan Lee Byeungwoo Jeon |
author_sort | Jeeyoon Park |
collection | DOAJ |
description | The recently published video coding standard, Versatile Video Coding (VVC/H.266), has the intra subpartition (ISP) coding mode, which divides an intra-predicted block into smaller blocks called subpartitions, each of which can be predicted using the newly reconstructed subpartition while still sharing the same intra mode. It is a VVC intra prediction tool that brings significant coding gains but also increases its encoding complexity. In this context, this paper addresses how to speed up the ISP encoding process by designing an ISP early skip decision scheme using a simple LightGBM model. The proposed ISP decision expedites the encoding process by early determination of whether or not to skip the ISP mode test. The proposed method uses the mean absolute sum of transform coefficients as a key feature. Our experimental results show an average encoding time saving of 7.2% under the all intra coding configuration with 0.08% BDBR loss. Compared to the state-of-the-art methods, our solution is able to outperform related works in terms of the combined rate-distortion and time saving. |
first_indexed | 2024-04-12T11:34:58Z |
format | Article |
id | doaj.art-085f1293085a4d4f86bf2ae61a723046 |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-04-12T11:34:58Z |
publishDate | 2022-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-085f1293085a4d4f86bf2ae61a7230462022-12-22T03:34:51ZengIEEEIEEE Access2169-35362022-01-011011105211106510.1109/ACCESS.2022.32151639921285Machine Learning-Based Early Skip Decision for Intra Subpartition Prediction in VVCJeeyoon Park0https://orcid.org/0000-0002-1554-5551Bumyoon Kim1https://orcid.org/0000-0002-9903-0896Jeehwan Lee2https://orcid.org/0000-0002-9757-5999Byeungwoo Jeon3https://orcid.org/0000-0002-5650-2881Department of Electrical and Computer Engineering, Sungkyunkwan University, Suwon, South KoreaDepartment of Electrical and Computer Engineering, Sungkyunkwan University, Suwon, South KoreaDepartment of Electrical and Computer Engineering, Sungkyunkwan University, Suwon, South KoreaDepartment of Electrical and Computer Engineering, Sungkyunkwan University, Suwon, South KoreaThe recently published video coding standard, Versatile Video Coding (VVC/H.266), has the intra subpartition (ISP) coding mode, which divides an intra-predicted block into smaller blocks called subpartitions, each of which can be predicted using the newly reconstructed subpartition while still sharing the same intra mode. It is a VVC intra prediction tool that brings significant coding gains but also increases its encoding complexity. In this context, this paper addresses how to speed up the ISP encoding process by designing an ISP early skip decision scheme using a simple LightGBM model. The proposed ISP decision expedites the encoding process by early determination of whether or not to skip the ISP mode test. The proposed method uses the mean absolute sum of transform coefficients as a key feature. Our experimental results show an average encoding time saving of 7.2% under the all intra coding configuration with 0.08% BDBR loss. Compared to the state-of-the-art methods, our solution is able to outperform related works in terms of the combined rate-distortion and time saving.https://ieeexplore.ieee.org/document/9921285/VVCintra predictionfast intra predictionH266/VVCencoder optimizationintra subpartition (ISP) |
spellingShingle | Jeeyoon Park Bumyoon Kim Jeehwan Lee Byeungwoo Jeon Machine Learning-Based Early Skip Decision for Intra Subpartition Prediction in VVC IEEE Access VVC intra prediction fast intra prediction H266/VVC encoder optimization intra subpartition (ISP) |
title | Machine Learning-Based Early Skip Decision for Intra Subpartition Prediction in VVC |
title_full | Machine Learning-Based Early Skip Decision for Intra Subpartition Prediction in VVC |
title_fullStr | Machine Learning-Based Early Skip Decision for Intra Subpartition Prediction in VVC |
title_full_unstemmed | Machine Learning-Based Early Skip Decision for Intra Subpartition Prediction in VVC |
title_short | Machine Learning-Based Early Skip Decision for Intra Subpartition Prediction in VVC |
title_sort | machine learning based early skip decision for intra subpartition prediction in vvc |
topic | VVC intra prediction fast intra prediction H266/VVC encoder optimization intra subpartition (ISP) |
url | https://ieeexplore.ieee.org/document/9921285/ |
work_keys_str_mv | AT jeeyoonpark machinelearningbasedearlyskipdecisionforintrasubpartitionpredictioninvvc AT bumyoonkim machinelearningbasedearlyskipdecisionforintrasubpartitionpredictioninvvc AT jeehwanlee machinelearningbasedearlyskipdecisionforintrasubpartitionpredictioninvvc AT byeungwoojeon machinelearningbasedearlyskipdecisionforintrasubpartitionpredictioninvvc |