Multitask Learning Based Intra-Mode Decision Framework for Versatile Video Coding - Université de Rennes Accéder directement au contenu
Article Dans Une Revue Electronics Année : 2022

Multitask Learning Based Intra-Mode Decision Framework for Versatile Video Coding

Résumé

In mid-2020, the new international video coding standard, namely versatile video coding (VVC), was officially released by the Joint Video Expert Team (JVET). As its name indicates, the VVC enables a higher level of versatility with better compression performance compared to its predecessor, high-efficiency video coding (HEVC). VVC introduces several new coding tools like multiple reference lines (MRL) and matrix-weighted intra-prediction (MIP), along with several improvements on the block-based hybrid video coding scheme such as quatree with nested multi-type tree (QTMT) and finer-granularity intra-prediction modes (IPMs). Because finding the best encoding decisions is usually preceded by optimizing the rate distortion (RD) cost, introducing new coding tools or enhancing existing ones requires additional computations. In fact, the VVC is 31 times more complex than the HEVC. Therefore, this paper aims to reduce the computational complexity of the VVC. It establishes a large database for intra-prediction and proposes a multitask learning (MTL)-based intra-mode decision framework. Experimental results show that our proposal enables up to 30% of complexity reduction while slightly increasing the Bjontegaard bit rate (BD-BR).
Fichier principal
Vignette du fichier
electronics-11-04001.pdf (804.22 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03923939 , version 1 (05-01-2023)

Licence

Paternité

Identifiants

Citer

Naima Zouidi, Amina Kessentini, Wassim Hamidouche, Nouri Masmoudi, Daniel Menard. Multitask Learning Based Intra-Mode Decision Framework for Versatile Video Coding. Electronics, 2022, 11 (23), pp.4001. ⟨10.3390/electronics11234001⟩. ⟨hal-03923939⟩
22 Consultations
14 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More