Advanced CNN Based Motion Compensation Fractional Interpolation
Advanced CNN Based Motion Compensation Fractional Interpolation
复制标题
DOI：
10.1109/icip.2019.8804199
复制
发表时间：
2019-09
期刊：
影响因子：
--
通讯作者：
Hang Zhang;Li Li-Li;Li Song;Xiaokang Yang;Zhu Li
中科院分区：
文献类型：
--
作者：
Hang Zhang;Li Li-Li;Li Song;Xiaokang Yang;Zhu Li
分数样本精度运动补偿已在一系列视频编码标准中广泛采用，以进一步提高压缩效率。通常，基于信号分解的插值滤波器用于从整数像素生成分数样本。然而，由于设计这些滤波器时的假设，这些有限脉冲响应滤波器的系数可能不适合变化的视频内容和编码条件。在本文中，我们将分数插值过程视为图像生成任务，它利用参考块处的真实整数位置样本来预测和生成更接近当前编码块的分数样本。我们使用卷积神经网络（CNN）作为生成器。此外，为了充分利用CNN强大的非线性学习能力，我们没有直接输入参考块，而是分别输入参考块相应的预测和残差部分。所提出的基于 CNN 的双输入插值方案已被纳入 HEVC 框架中，实验结果表明我们的方法实现了平均 0.9% 的比特率降低。
Fractional-sample precision motion compensation has been widely adopted in a series of video coding standards to further improve compression efficiency. Usually, signal decomposition based interpolation filters are used to generate fractional samples from integer pixels. However, the coefficients of these finite impluse response filters may not be suitable for varied video contents and coding conditions because of the assumption when designing these filters. In this paper, we regard the fractional interpolation process as an image generation task, which utilizes the real interger position samples at the reference block to predict and generate fractional samples that are much closer to current coding block. We use the con-volutional neural netwok (CNN) as the generator. Moreover, to make the best of CNN’s powerful nonlinear learning ability, instead of inputting the reference block directly, we separately input the corresponding prediction and residual parts of reference block. The proposed dual-input CNN-based interpolation scheme has been incorporated into the HEVC framework and experimental results demonstrate our approach achieves average 0.9% bitrate reduction.