Reference Frame Generation Algorithm using Dynamical Learning PredNet for VVC
Reference Frame Generation Algorithm using Dynamical Learning PredNet for VVC
复制标题
DOI：
10.1109/icce50685.2021.9427694
复制
发表时间：
2021-01
期刊：
影响因子：
--
通讯作者：
Takafumi Katayama;Tian Song;T. Shimamoto;Xiantao Jiang
中科院分区：
文献类型：
--
作者：
Takafumi Katayama;Tian Song;T. Shimamoto;Xiantao Jiang
参考帧对于通用视频编码（VVC）中帧间预测的编码效率起着重要作用。特别是，非线性运动的预测对运动补偿来说是一个挑战。在本文中，我们提出了一种使用动态学习 PredNet 进行帧间预测的新参考帧生成算法。所提出的包括训练和推理的 PredNet 被实现到 VVC 编码器中的帧缓冲区。所提出的VVC编码器是通过流水线处理实现的。仿真结果表明，与原始VVC算法相比，该算法可以实现0.58%的BD-rate提升。
The reference frame plays an important role in the coding efficiency of inter-frame prediction in versatile video coding (VVC). In particular, the prediction of non-linear motion is a challenge for the motion compensation. In this paper, we proposed a new reference frame generation algorithm using dynamical learning PredNet for the inter prediction. The proposed PredNet which include training and inference is implemented to frame buffer in the VVC encoder. The proposed VVC encoder is achieved by the pipeline processing. The simulation results show that the proposed algorithm can achieve an improvement of 0.58% BD-rate comparing to the original VVC algorithm.