CNN oriented fast QTBT partition algorithm for JVET intra coding

Zhang, Jin; An, Ping; Shen, Liquan; Yang, Chao

doi:10.1109/vcip.2017.8305020

Cited by 48 publications

(36 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The technique proposed by Lin et al [31] skips the BT Rate Distorsion Optimization (RDO) process of the second sub-CU, when the RD cost of the parent CU and the first sub CU fulfil certain constraints. Authors in [32] and [33], use CNNs to predict a depth description of QTBT partition of the CTUs. In [32], the CNN takes as an input the 32 × 32 pixels blocks of the frame, as well as QP value, and outputs a class from 0 to 5 describing QTBT partition depth for AI configuration.…”

Section: B Complexity Reduction Of Frame Partitioningmentioning

confidence: 99%

“…Authors in [32] and [33], use CNNs to predict a depth description of QTBT partition of the CTUs. In [32], the CNN takes as an input the 32 × 32 pixels blocks of the frame, as well as QP value, and outputs a class from 0 to 5 describing QTBT partition depth for AI configuration. In [33], the false prediction risk of CNN is controlled based on temporal correlation for RA configuration.…”

Section: B Complexity Reduction Of Frame Partitioningmentioning

confidence: 99%

“…Unlike previously mentioned techniques speeding up the QTBT partition scheme, the proposed solution is tunable and offers various complexity reduction opportunities, from 30% to 70% in average. Moreover, this solution can be considered as lightweight since it relies on RF classifiers, inducing much smaller overhead compared to CNN based techniques [32] [33].…”

Section: B Complexity Reduction Of Frame Partitioningmentioning

confidence: 99%

See 2 more Smart Citations

Tunable VVC Frame Partitioning Based on Lightweight Machine Learning

Amestoy

Mercat

Hamidouche

et al. 2020

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Block partition structure is a critical module in video coding scheme to achieve significant gap of compression performance. Under the exploration of the future video coding standard, named Versatile Video Coding (VVC), a new Quad Tree Binary Tree (QTBT) block partition structure has been introduced. In addition to the QT block partitioning defined in High Efficiency Video Coding (HEVC) standard, new horizontal and vertical BT partitions are enabled, which drastically increases the encoding time compared to HEVC. In this paper, we propose a lightweight and tunable QTBT partitioning scheme based on a Machine Learning (ML) approach. The proposed solution uses Random Forest classifiers to determine for each coding block the most probable partition modes. To minimize the encoding loss induced by misclassification, risk intervals for classifier decisions are introduced in the proposed solution. By varying the size of risk intervals, tunable trade-off between encoding complexity reduction and coding loss is achieved. The proposed solution implemented in the JEM-7.0 software offers encoding complexity reductions ranging from 30% to 70% in average for only 0.7% to 3.0% Bjøntegaard Delta Rate (BD-BR) increase in Random Access (RA) coding configuration, with very slight overhead induced by Random Forest. The proposed solution based on Random Forest classifiers is also efficient to reduce the complexity of the Multi-Type Tree (MTT) partitioning scheme under the VTM-5.0 software, with complexity reductions ranging from 25% to 61% in average for only 0.4% to 2.2% BD-BR increase.

show abstract

Section: B Complexity Reduction Of Frame Partitioningmentioning

confidence: 99%

Section: B Complexity Reduction Of Frame Partitioningmentioning

confidence: 99%

Section: B Complexity Reduction Of Frame Partitioningmentioning

confidence: 99%

See 1 more Smart Citation

Tunable VVC Frame Partitioning Based on Lightweight Machine Learning

Amestoy

Mercat

Hamidouche

et al. 2020

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…A local-constrained QTBT scheme was proposed by dynamically deriving the partition parameters for each CTU [135]. A CNNbased fast QTBT algorithm was presented [136], in which QTBT depth range is modeled as a multi-class classification problem This is the author's version of an article that has been published in this journal. Changes were made to this version by the publisher prior to publication.…”

Section: A Quadtree Plus Binary Tree (Qtbt) Block Partitioningmentioning

confidence: 99%

Recent Advances on HEVC Inter-Frame Coding: From Optimization to Implementation and Beyond

Zhang

Fan

et al. 2020

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

High Efficiency Video Coding (HEVC) has doubled the video compression ratio with equivalent subjective quality as compared to its predecessor H.264/AVC. The significant coding efficiency improvement is attributed to many new techniques. Interframe coding is one of the most powerful yet complicated techniques therein and has posed high computational burden thus main obstacle in HEVC-based real-time applications. Recently, plenty of research has been done to optimize the inter-frame coding, either to reduce the complexity for real-time applications, or to further enhance the encoding efficiency. In this paper, we provide a comprehensive review of the state-of-the-art techniques for HEVC inter-frame coding from three aspects, namely fast inter coding solutions, implementation on different hardware platforms as well as advanced inter coding techniques. More specifically, different algorithms in each aspect are further subdivided into sub-categories and compared in terms of pros, cons, coding efficiency and coding complexity. To the best of our knowledge, this is the first such comprehensive review of the recent advances of the inter-frame coding for HEVC and hopefully it would help the improvement, implementation and applications of HEVC as well as the ongoing development of the next generation video coding standard.

show abstract

“…The [29]- [33] algorithms based on deep learning or machine learning can accelerate coding in H.266/VVC. Fast CU depth decision schemes are introduced in [29][30], which modeled the depth range as a multi-class classification problem to accelerate intra coding in H.266/VVC. An adaptive CU partition decision algorithm based on H.266/VVC is developed in [31], which uses variable CNN to optimize CU partition and avoid the calculation of full RD.…”

Section: Introductionmentioning

confidence: 99%

Fast CU Partition and Intra Mode Decision Method for H.266/VVC

et al. 2020

View full text Add to dashboard Cite

The Versatile Video Coding (H.266/VVC) standard has developed by Joint Video Exploration Team (JVET). Compared with the previous generation video coding standard, the H.266/VVC is more outstanding. Since the H.266/VVC introduces multi-type tree (MTT) structure including binary tree (BT) and ternary tree (TT), which brings the significant coding efficiency but increases coding complexity. Moreover, the intra prediction modes have increased from 35 to 67, which can provide more accurate prediction than H.265/High Efficiency Video Coding (HEVC). Therefore, these can improve the encoding quality, but increase computational complexity. To reduce the computational complexity, this paper designs a fast coding unit (CU) partition and intra mode decision algorithm, which includes fast CU partition based on random forest classifier (RFC) model and fast intra prediction modes optimization based on texture region features. Simulation results indicate that the proposed scheme can save 54.91% encoding time with only 0.93% increase in BDBR. INDEX TERMS H.266/VVC, fast CU partition, intra mode decision, random forest, texture feature

show abstract

CNN oriented fast QTBT partition algorithm for JVET intra coding

Cited by 48 publications

References 9 publications

Tunable VVC Frame Partitioning Based on Lightweight Machine Learning

Tunable VVC Frame Partitioning Based on Lightweight Machine Learning

Recent Advances on HEVC Inter-Frame Coding: From Optimization to Implementation and Beyond

Fast CU Partition and Intra Mode Decision Method for H.266/VVC

Contact Info

Product

Resources

About