Recently, learned video compression has achieved exciting performance. Following the traditional hybrid prediction coding framework, most learned methods generally adopt the motion estimation motion compensation (MEMC) method to remove inter-frame redundancy. However, inaccurate motion vector (MV) usually lead to the distortion of reconstructed frame. In addition, most approaches ignore the spatial and channel redundancy. To solve above problems, we propose a motion-aware and spatial-temporal-channel contextual coding based video compression network (MASTC-VC), which learns the latent representation and uses variational autoencoders (VAEs) to capture the characteristics of intra-frame pixels and inter-frame motion. Specifically, we design a multiscale motion-aware module (MS-MAM) to estimate spatial-temporal-channel consistent motion vector by utilizing the multiscale motion prediction information in a coarse-to-fine way. On the top of it, we further propose a spatial-temporal-channel contextual module (STCCM), which explores the correlation of latent representation to reduce the bit consumption from spatial, temporal and channel aspects respectively. Comprehensive experiments show that our proposed MASTC-VC is surprior to previous state-of-the-art (SOTA) methods on three public benchmark datasets. More specifically, our method brings average 10.15\% BD-rate savings against H.265/HEVC (HM-16.20) in PSNR metric and average 23.93\% BD-rate savings against H.266/VVC (VTM-13.2) in MS-SSIM metric.

翻译：近期，学习式视频压缩取得了令人瞩目的进展。遵循传统混合预测编码框架，多数学习方法通常采用运动估计与运动补偿（MEMC）方法去除帧间冗余。然而，不准确的运动矢量（MV）常导致重建帧失真。此外，大多数方法忽视了空间与通道冗余。针对上述问题，本文提出一种基于运动感知与时空通道上下文编码的视频压缩网络（MASTC-VC），该网络通过学习隐式表征，利用变分自编码器（VAEs）捕捉帧内像素与帧间运动特征。具体而言，我们设计了一个多尺度运动感知模块（MS-MAM），通过采用由粗到精的方式利用多尺度运动预测信息，估计时空通道一致的运动矢量。在此基础上，进一步提出时空通道上下文模块（STCCM），该模块从空间、时间与通道三个维度分别探索隐式表征的相关性，以降低比特消耗。综合实验表明，我们提出的MASTC-VC在三个公开基准数据集上均优于现有最先进（SOTA）方法。具体而言，在PSNR指标下，本方法相比H.265/HEVC（HM-16.20）平均节省10.15%的BD-rate；在MS-SSIM指标下，相比H.266/VVC（VTM-13.2）平均节省23.93%的BD-rate。