Reducing complexity in versatile video coding intra-coding through machine learning-based optimization of partitioning and prediction.
Saved in:
| Title: | Reducing complexity in versatile video coding intra-coding through machine learning-based optimization of partitioning and prediction. |
|---|---|
| Authors: | KESSENTINI, Amina1 ksontini.amina@gmail.com, MARAOUI, Amna2, WERDA, Imen1, SAYADI, Fatma Ezahra2 |
| Source: | Turkish Journal of Electrical Engineering & Computer Sciences. 2026, Vol. 34 Issue 2, p248-263. 16p. |
| Subject Terms: | *Video coding, *Machine learning, *Decision trees, *Video compression, *Rate distortion theory, *Artificial neural networks |
| Abstract: | The escalating demand for high-resolution multimedia content has necessitated more efficient video compression solutions. The versatile video coding (VVC) standard, despite achieving remarkable compression gains, introduces significant computational complexity, primarily due to its exhaustive rate-distortion optimization (RDO) process. To address this, we propose an intelligent approach leveraging supervised machine learning techniques to streamline the VVC encoding process. Specifically, we introduce a lightweight neural network (LNN) for efficient coding unit partitioning decisions and a decision tree (DT) classifier for optimizing the intra prediction process. This dual-method framework, tailored for All Intra coding configurations, significantly reduces encoder complexity while maintaining compression performance and visual quality. Through extensive testing, we demonstrate a remarkable 65.47% reduction in encoding time with minimal impact on compression efficiency and no perceptible degradation in video quality. These findings represent a significant step towards making high-efficiency VVC encoding more practical for real-world applications. [ABSTRACT FROM AUTHOR] |
| Database: | Energy & Power Source |
| FullText | Links: – Type: pdflink Text: Availability: 0 |
|---|---|
| Header | DbId: enr DbLabel: Energy & Power Source An: 192447966 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Reducing complexity in versatile video coding intra-coding through machine learning-based optimization of partitioning and prediction. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22KESSENTINI%2C+Amina%22">KESSENTINI, Amina</searchLink><relatesTo>1</relatesTo><i> ksontini.amina@gmail.com</i><br /><searchLink fieldCode="AR" term="%22MARAOUI%2C+Amna%22">MARAOUI, Amna</searchLink><relatesTo>2</relatesTo><br /><searchLink fieldCode="AR" term="%22WERDA%2C+Imen%22">WERDA, Imen</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22SAYADI%2C+Fatma+Ezahra%22">SAYADI, Fatma Ezahra</searchLink><relatesTo>2</relatesTo> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Turkish+Journal+of+Electrical+Engineering+%26+Computer+Sciences%22">Turkish Journal of Electrical Engineering & Computer Sciences</searchLink>. 2026, Vol. 34 Issue 2, p248-263. 16p. – Name: Subject Label: Subject Terms Group: Su Data: *<searchLink fieldCode="DE" term="%22Video+coding%22">Video coding</searchLink><br />*<searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br />*<searchLink fieldCode="DE" term="%22Decision+trees%22">Decision trees</searchLink><br />*<searchLink fieldCode="DE" term="%22Video+compression%22">Video compression</searchLink><br />*<searchLink fieldCode="DE" term="%22Rate+distortion+theory%22">Rate distortion theory</searchLink><br />*<searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: The escalating demand for high-resolution multimedia content has necessitated more efficient video compression solutions. The versatile video coding (VVC) standard, despite achieving remarkable compression gains, introduces significant computational complexity, primarily due to its exhaustive rate-distortion optimization (RDO) process. To address this, we propose an intelligent approach leveraging supervised machine learning techniques to streamline the VVC encoding process. Specifically, we introduce a lightweight neural network (LNN) for efficient coding unit partitioning decisions and a decision tree (DT) classifier for optimizing the intra prediction process. This dual-method framework, tailored for All Intra coding configurations, significantly reduces encoder complexity while maintaining compression performance and visual quality. Through extensive testing, we demonstrate a remarkable 65.47% reduction in encoding time with minimal impact on compression efficiency and no perceptible degradation in video quality. These findings represent a significant step towards making high-efficiency VVC encoding more practical for real-world applications. [ABSTRACT FROM AUTHOR] |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=enr&AN=192447966 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.55730/1300-0632.4173 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 16 StartPage: 248 Subjects: – SubjectFull: Video coding Type: general – SubjectFull: Machine learning Type: general – SubjectFull: Decision trees Type: general – SubjectFull: Video compression Type: general – SubjectFull: Rate distortion theory Type: general – SubjectFull: Artificial neural networks Type: general Titles: – TitleFull: Reducing complexity in versatile video coding intra-coding through machine learning-based optimization of partitioning and prediction. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: KESSENTINI, Amina – PersonEntity: Name: NameFull: MARAOUI, Amna – PersonEntity: Name: NameFull: WERDA, Imen – PersonEntity: Name: NameFull: SAYADI, Fatma Ezahra IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 03 Text: 2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 13000632 Numbering: – Type: volume Value: 34 – Type: issue Value: 2 Titles: – TitleFull: Turkish Journal of Electrical Engineering & Computer Sciences Type: main |
| ResultId | 1 |
