Neural Video Coding Using Multiscale Motion Compensation and Spatiotemporal Context Model

Haojie Liu, Ming Lu, Zhan Ma, Fan Wang, Zhihuang Xie, Xun Cao, Yao Wang

Research output: Contribution to journalArticlepeer-review


Over the past two decades, traditional block-based video coding has made remarkable progress and spawned a series of well-known standards such as MPEG-4, H.264/AVC and H.265/HEVC. On the other hand, deep neural networks (DNNs) have shown their powerful capacity for visual content understanding, feature extraction and compact representation. Some previous works have explored the learnt video coding algorithms in an end-to-end manner, which show the great potential compared with traditional methods. In this paper, we propose an end-to-end deep neural video coding framework (NVC), which uses variational autoencoders (VAEs) with joint spatial and temporal prior aggregation (PA) to exploit the correlations in intra-frame pixels, inter-frame motions and inter-frame compensation residuals, respectively. Novel features of NVC include: 1) To estimate and compensate motion over a large range of magnitudes, we propose an unsupervised multiscale motion compensation network (MS-MCN) together with a pyramid decoder in the VAE for coding motion features that generates multiscale flow fields, 2) we design a novel adaptive spatiotemporal context model for efficient entropy coding for motion information, 3) we adopt nonlocal attention modules (NLAM) at the bottlenecks of the VAEs for implicit adaptive feature extraction and activation, leveraging its high transformation capacity and unequal weighting with joint global and local information, and 4) we introduce multi-module optimization and a multi-frame training strategy to minimize the temporal error propagation among P-frames. NVC is evaluated for the low-delay causal settings and compared with H.265/HEVC, H.264/AVC and the other learnt video compression methods following the common test conditions, demonstrating consistent gains across all popular test sequences for both PSNR and MS-SSIM distortion metrics.

Original languageEnglish (US)
Article number9247134
Pages (from-to)3182-3196
Number of pages15
JournalIEEE Transactions on Circuits and Systems for Video Technology
Issue number8
StatePublished - Aug 2021


  • Neural video coding
  • multiscale compressed flows
  • multiscale motion compensation
  • neural network
  • nonlocal attention
  • pyramid decoder
  • spatiotemporal priors
  • temporal error propagation

ASJC Scopus subject areas

  • Media Technology
  • Electrical and Electronic Engineering


Dive into the research topics of 'Neural Video Coding Using Multiscale Motion Compensation and Spatiotemporal Context Model'. Together they form a unique fingerprint.

Cite this