.png){kind=icon}
返回
Fast coding unit size decision based on deep reinforcement learning for versatile video coding
.png){kind=icon}
PRE
AI
DOI：10.1007/s11042-022-12558-z.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Video coding has long been looking for a more available approach than the greedy method. The quad-tree with nested multi-type tree (QTMT) structure including quad-tree (QT) and multi-type tree (MTT) results in highly coding complexity in Versatile Video Coding (VVC). In addition, the rapid progress in deep learning (DL) is attracting increasing attention in the video coding community. Therefore, this paper proposes a fast Coding Unit (CU) splitting decision method based on Deep reinforcement learning (DRL) for VVC to decrease the coding complexity. Specifically, the 32 x 32 CU for splitting is considered as a Markov decision process (MDP), the CU splitting situations at a certain node as state, the splitting modes decision as actions, the reduction or increase in rate-distortion (RD) cost as the immediate rewards or punishments, and the encoder as an agent to make coding decisions successively. The simulation results demonstrate that the coding time reduction (CTR) of the proposed approach can lead to a reduction of about 54.38% while maintaining coding performance, which can realize a trade-off between the complexity reduction and coding efficiency.
Keyword:
CU size decision
Reinforcement learning
Deep reinforcement learning
Markov decision processing
期刊
IF:
3
论文数:
2.0W
被引数:
3.2W
机构
引用论文
Efficacy and safety of PARP inhibitors for maintenance treatment of ovarian cancer, regardless of BRCA or HRD status: a comprehensive updated meta-analysisPARP抑制剂用于卵巢癌维持治疗的有效性和安全性，无论BRCA或HRD状态如何：一项全面的更新Meta分析
OAAI
OAAI分享收藏IBOA‐Based Optimization of Cross‐Sectional Dimension of Rods for a 3‐RRR PPM to Minimize Energy Consumption.png)
ComplexityOAAI
ComplexityIF0
OAAI分享收藏The Importance of Contrast Enhancement in Medical Images Analysis and Diagnosis医学图像分析与诊断中对比度增强的重要性OAAI
OAAI分享收藏AI Data Readiness Inspector (AIDRIN) for Quantitative Assessment of Data Readiness for AIProceedings of the 36th International Conference on Scientific and Statistical Database ManagementOAAI
Proceedings of the 36th International Conference on Scientific and Statistical Database ManagementIF0
OAAI分享收藏
Improved enteral tolerance following step procedure: systematic literature review and meta-analysis
PREAI
分享收藏
查看更多内容