基于卷积神经网络的分数像素运动补偿

Convolutional neural network-based fractional-pixel motion compenstaion

分数阶插值是帧间编码运动补偿中一项重要技术。为改进传统插值滤波器插值效果不佳,现有基于深度学习的方法存在只生成半像素样本、需要对各个分像素位置及量化参数(QP)训练相应模型、需引入额外的信息作为输入等不足之处,本文提出一种用于帧间编码分数像素运动补偿的卷积神经网络(CNN)方法。首先以残差稠密网络为基础,然后联合多尺度失真特征提取结构及亚像素卷积来增加特征提取准确性和生成分数像素。为了训练所提出的网络,本文分析该分数阶插值任务的特点,构建了带有真实性失真的数据集。该模型依靠参考帧生成各个位置的分数像素样本,且适应任意的量化参数。实验结果表明,与H.265/HEVC相比可以节省更多的比特数。在低延迟P(LDP)的配置下,平均降低2%的BD-rate,与同类方法相比综合性能也有所提升。

A convolutional neural network(CNN)for fractional interpolation of inter prediction is proposed because of the poor interpolation effect of traditional interpolation filters and the deep learning methods,which only generate half pixel samples,or need to train the corresponding model for each pixel position and quantization parameter(QP),or introduce additional information as input.Based on the dense residual network,the model combines multi-scale distortion feature extraction structure and sub-pixel convolution to increase the accuracy of feature extraction and generate fractional pixels.The characteristics of fractional interpolation task are analyzed and the data set with true distortion is constructed.The model directly generates fractional pixel samples and can adapt to arbitrary quantization parameters(QP).Experimental results verify the efficiency of the method.Compared with H.265/HEVC,this method achieves 2%in bit saving on average under low-delay P configuration.Compared with similar methods,the overall performance has also been improved.