Saliency-Enabled Coding Unit Partitioning and Quantization Control for Versatile Video Coding
The latest video coding standard, versatile video coding (VVC), has greatly improved coding efficiency over its predecessor standard high efficiency video coding (HEVC), but at the expense of sharply increased complexity.
Wei Li +4 more
doaj +1 more source
A fast CU partition algorithm of ERP 360‐degree video based on deep learning
The main contributions of this article include three aspects. (1) Establishing a training and validation dataset with latitudinal and quantized parameter characteristics, (2) designing a lightweight convolutional neural network for predicting coding unit (CU) partition, and (3) developing a decision‐making algorithm capable of predicting partitioning ...
Hai Xiang +3 more
wiley +1 more source
VVC in the cloud and browser playback
1924The most recent international video coding standard that was developed jointly by the ITU-T and ISO/IEC is Versatile Video Coding (VVC). While VVC contains a feature set for a very wide range of applications it also allows for significant bit-rate ...
Hege, Gabriel +13 more
core +1 more source
Latitude‐Guided Adaptive Inter‐Frame CU Partitioning for Fast Panoramic Video Encoding
This letter proposes a multi‐feature attentive convolutional neural network (MFA‐CNN)‐based fast coding unit (CU) partitioning algorithm for panoramic video inter‐coding in versatile video coding (VVC). To address coding efficiency in panoramic videos, the algorithm employs latitude‐guided adaptive partitioning threshold and dynamic quantisation ...
Wenjun Zheng +3 more
wiley +1 more source
VVC Complexity and Software Implementation Analysis
S.3765-3778A steady increase in available processing power continues to drive advances in video compression technology. The recently completed Versatile Video Coding (VVC) standard aims to double the compression efficiency of HEVC and deliver a same ...
Suhring, K. +3 more
core +1 more source
Design of Efficient Perspective Affine Motion Estimation/Compensation for Versatile Video Coding (VVC) Standard [PDF]
The fundamental motion model of the conventional block-based motion compensation in High Efficiency Video Coding (HEVC) is a translational motion model. However, in the real world, the motion of an object exists in the form of combining many kinds of motions.
Young-Ju Choi +3 more
openaire +1 more source
Image Compression Model Based on Dynamic Convolution and Vision Mamba
An end‐to‐end image compression model integrates Vision Mamba and omni‐dimensional dynamic convolution. Enhancements to the variational autoencoder‐based framework improved its global information modelling. Two models, lightweight and heavyweight, are designed to compete with the methods of recent years.
Lingchen Qiu +4 more
wiley +1 more source
Low Complexity Decision Algorithm for CU Partition Based on Image Texture Information and LGBM
In order to solve the problem of insufficient compression efficiency of High-Efficiency Video coding (HEVC) in the current video market, a new generation of Versatile Video Coding (VVC) has been proposed. However, the newly added Multi-Type Tree (MTT) in
Erlin Tian, Xiaowei Qian, Qiuwen Zhang
doaj +1 more source
Storage‐and‐Memory‐Efficient Learned Image Compression With Quality‐Aware Hyperprior Pruning
We propose a quality‐aware hyperprior pruning method that efficiently reduces the storage and memory cost of the hyperprior module. It consists of two parts. The first part is a hyperprior pruning method, called enhanced ResRep on hyper path, which expands a channel pruning method to fundamental components in the hyperprior module of recent learned ...
Ao Luo +4 more
wiley +1 more source
Context-Based Ternary Tree Decision Method in Versatile Video Coding for Fast Intra Coding
This paper presents a fast encoding method for versatile video coding (VVC) using an early determination scheme that skips redundant multi-type tree (MTT) pruning. MTT consists of binary and ternary trees (TTs) with traditional quadtrees and has recently
Sang-Hyo Park, Je-Won Kang
doaj +1 more source

