基于群变分变换神经网络的分数阶插值视频编码
A Group Variational Transformation Neural Network for Fractional Interpolation of Video Coding
摘要:
运动补偿是视频编码中的一项重要技术,用于消除已编码视频帧之间的时间冗余。在运动补偿中,分数插值用于在亚像素级获得更多的参考块。现有的视频编码标准通常使用固定的插值滤波器进行分数插值,其效率不足以很好地处理不同的视频信号。本文设计了一种群变分变换卷积神经网络(GVTCNN)来提高运动补偿中亮度分量的分数插值性能。GVTCNN从输入整数位置样本推断不同子像素位置处的样本。它首先从整数位置样本中提取一个共享的特征图来推断各种子像素位置样本。然后,使用组变分变换技术将一组复制的共享特征图变换为不同子像素位置处的样本。实验结果表明,我们的GVTCNN的插值效率。与高效视频编码的插值方法相比,该方法平均节省比特1.9%,在低延迟P配置下节省比特高达5.6%。
英文摘要:
Motion compensation is an important technology in video coding to remove the temporal redundancy between coded video frames. In motion compensation, fractional interpolation is used to obtain more reference blocks at sub-pixel level. Existing video coding standards commonly use fixed interpolation filters for fractional interpolation, which are not efficient enough to handle diverse video signals well. In this paper, we design a group variational transformation convolutional neural network (GVTCNN) to improve the fractional interpolation performance of the luma component in motion compensation. GVTCNN infers samples at different sub-pixel positions from the input integer-position sample. It first extracts a shared feature map from the integer-position sample to infer various sub-pixel position samples. Then a group variational transformation technique is used to transform a group of copied shared feature maps to samples at different sub-pixel positions. Experimental results have identified the interpolation efficiency of our GVTCNN. Compared with the interpolation method of High Efficiency Video Coding, our method achieves 1.9% bit saving on average and up to 5.6% bit saving under low-delay P configuration.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。