Low-complexity intra coding algorithm based on convolutional neural network for HEVC
Low-complexity intra coding algorithm based on convolutional neural network for HEVC
复制标题
DOI：
10.1109/infoct.2018.8356852
复制
发表时间：
2018-03
期刊：
影响因子：
--
通讯作者：
Takafumi Katayama;Kazuki Kuroda;Wen Shi;Tian Song;T. Shimamoto
中科院分区：
文献类型：
--
作者：
Takafumi Katayama;Kazuki Kuroda;Wen Shi;Tian Song;T. Shimamoto
提出了一种基于卷积神经网络的高效视频编码（HEVC）中编码单元（CU）大小快速决策算法。提出的快速算法有助于减少不少于两个CU划分模式，在每个编码树单元的全面率失真优化处理，从而降低编码器的硬件复杂度。此外，我们的算法只使用纹理信息，它不依赖于CU深度或空间附近的CU之间的相关性。该方法有利于并行处理，提高了RDO的流水线处理能力。所提出的算法在HEVC（HM16.7）的参考软件中实现。仿真结果表明，与原HEVC算法相比，该算法的计算复杂度降低了67.3%以上。
In this paper, we propose a fast coding unit (CU) size decision algorithm for high efficiency video coding (HEVC) based on convolutional neural network. The proposed fast algorithm contributes to decrease no less than two CU partition modes in each coding tree unit for full rate-distortion optimization processing, thereby reducing the encoder hardware complexity. Moreover, our algorithm use only texture information and it does not depend on the correlations among CU depths or spatially nearby CUs. It is friendly to the parallel processing and it can improve the pipeline process of RDO. The proposed algorithm is implemented in the reference software of HEVC (HM16.7). The simulation results show that the proposed algorithm can achieve over 67.3% computation complexity reduction comparing to the original HEVC algorithm.