Research on frame prediction technology of video coding based on convolutional neural network
Tianyu Zhang, Qiang Zhang, Ming Song, Zhenfu Yao · 2024
With the development of communication technology and Internet technology, the popularity of mobile terminals and intelligent devices, as well as emerging multimedia applications such as virtual reality video and short video, which enrich people’s daily life, video data is growing explosively. Although the current digital video coding standard HEVC can meet the compression performance requirements of high-definition and ultra-high definition digital videos, it cannot achieve good prediction results for complex texture image blocks or image blocks with weak directionality. In order to improve the accuracy of predictions in existing video coding standards, this paper proposes a prediction method based on convolutional neural networks. The experimental results show that the proposed prediction algorithm can achieve a $3.4 \%$ BD rate savings and a 0.29 dB BD-PSNR improvement.