Linear Multivariate Decision Trees for Fast QTMT Partitioning in VVC
The demand for ultra-high definition (UHD) content has led to the development of advanced compression tools to enhance the efficiency of standard codecs. One such tool is the Quaternary Tree and Multi-Type Tree (QTMT) used in the Versatile Video Coding (VVC), which significantly improves coding effi...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Open Journal of Signal Processing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10840301/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823859648151683072 |
|---|---|
| author | Jose N. Filipe Luis M. N. Tavora Sergio M. M. Faria Antonio Navarro Pedro A. A. Assuncao |
| author_facet | Jose N. Filipe Luis M. N. Tavora Sergio M. M. Faria Antonio Navarro Pedro A. A. Assuncao |
| author_sort | Jose N. Filipe |
| collection | DOAJ |
| description | The demand for ultra-high definition (UHD) content has led to the development of advanced compression tools to enhance the efficiency of standard codecs. One such tool is the Quaternary Tree and Multi-Type Tree (QTMT) used in the Versatile Video Coding (VVC), which significantly improves coding efficiency over previous standards, but introduces substantially higher computational complexity. To address the challenge of reducing computational complexity with minimal impact on coding efficiency, this paper presents a novel approach for intra-coding 360<inline-formula><tex-math notation="LaTeX">$^{\circ }$</tex-math></inline-formula> video in Equirectangular Projection (ERP) format. By exploiting distinct complexity and spatial characteristics of the North, Equator, and South regions in ERP images, the proposed method is devised upon a region-based approach, using novel linear multivariate decision trees to determine whether a given partition type can be skipped. Optimisation of model parameters and an adaptive thresholding method is also presented. The experimental results show a Complexity Gain of approximately 16% with a negligible BD-Rate loss of only 0.06%, surpassing current state-of-the-art methods in terms of complexity gain per percentage point of BD-Rate loss. |
| format | Article |
| id | doaj-art-db4d4ffb0022428182560ce6f4d8a13e |
| institution | Kabale University |
| issn | 2644-1322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Signal Processing |
| spelling | doaj-art-db4d4ffb0022428182560ce6f4d8a13e2025-02-11T00:01:48ZengIEEEIEEE Open Journal of Signal Processing2644-13222025-01-01617518310.1109/OJSP.2025.352889710840301Linear Multivariate Decision Trees for Fast QTMT Partitioning in VVCJose N. Filipe0https://orcid.org/0000-0002-9421-8072Luis M. N. Tavora1https://orcid.org/0000-0002-8580-1979Sergio M. M. Faria2https://orcid.org/0000-0002-0993-9124Antonio Navarro3https://orcid.org/0000-0002-8692-943XPedro A. A. Assuncao4https://orcid.org/0000-0001-9539-8311Universidade de Aveiro, Aveiro, PortugalInstituto Politécnico de Leiria, Leiria, PortugalInstituto Politécnico de Leiria, Leiria, PortugalUniversidade de Aveiro, Aveiro, PortugalInstituto Politécnico de Leiria, Leiria, PortugalThe demand for ultra-high definition (UHD) content has led to the development of advanced compression tools to enhance the efficiency of standard codecs. One such tool is the Quaternary Tree and Multi-Type Tree (QTMT) used in the Versatile Video Coding (VVC), which significantly improves coding efficiency over previous standards, but introduces substantially higher computational complexity. To address the challenge of reducing computational complexity with minimal impact on coding efficiency, this paper presents a novel approach for intra-coding 360<inline-formula><tex-math notation="LaTeX">$^{\circ }$</tex-math></inline-formula> video in Equirectangular Projection (ERP) format. By exploiting distinct complexity and spatial characteristics of the North, Equator, and South regions in ERP images, the proposed method is devised upon a region-based approach, using novel linear multivariate decision trees to determine whether a given partition type can be skipped. Optimisation of model parameters and an adaptive thresholding method is also presented. The experimental results show a Complexity Gain of approximately 16% with a negligible BD-Rate loss of only 0.06%, surpassing current state-of-the-art methods in terms of complexity gain per percentage point of BD-Rate loss.https://ieeexplore.ieee.org/document/10840301/Video coding complexityversatile video codingfast codingomnidirectional video |
| spellingShingle | Jose N. Filipe Luis M. N. Tavora Sergio M. M. Faria Antonio Navarro Pedro A. A. Assuncao Linear Multivariate Decision Trees for Fast QTMT Partitioning in VVC IEEE Open Journal of Signal Processing Video coding complexity versatile video coding fast coding omnidirectional video |
| title | Linear Multivariate Decision Trees for Fast QTMT Partitioning in VVC |
| title_full | Linear Multivariate Decision Trees for Fast QTMT Partitioning in VVC |
| title_fullStr | Linear Multivariate Decision Trees for Fast QTMT Partitioning in VVC |
| title_full_unstemmed | Linear Multivariate Decision Trees for Fast QTMT Partitioning in VVC |
| title_short | Linear Multivariate Decision Trees for Fast QTMT Partitioning in VVC |
| title_sort | linear multivariate decision trees for fast qtmt partitioning in vvc |
| topic | Video coding complexity versatile video coding fast coding omnidirectional video |
| url | https://ieeexplore.ieee.org/document/10840301/ |
| work_keys_str_mv | AT josenfilipe linearmultivariatedecisiontreesforfastqtmtpartitioninginvvc AT luismntavora linearmultivariatedecisiontreesforfastqtmtpartitioninginvvc AT sergiommfaria linearmultivariatedecisiontreesforfastqtmtpartitioninginvvc AT antonionavarro linearmultivariatedecisiontreesforfastqtmtpartitioninginvvc AT pedroaaassuncao linearmultivariatedecisiontreesforfastqtmtpartitioninginvvc |