Learning for Video Compression

Learning for Video Compression
复制标题

学习视频压缩

DOI:
10.1109/tcsvt.2019.2892608
复制
发表时间:
2018-04
影响因子:
8.4
通讯作者:
Wu Feng
Wu Feng
中科院分区:
工程技术1区
文献类型:
--
作者:
Chen Zhibo;He Tianyu;Jin Xin;Wu Feng

文献摘要

参考文献

被引文献

相似文献

基于学习的视频压缩的一个关键挑战是,运动预测编码,一个非常有效的视频压缩工具,很难被训练成一个神经网络。在本文中,我们提出了PixelMotionCNN(PMCNN)的概念,它包括运动扩展和混合预测网络。PMCNN可以对时空相干性进行建模,以有效地在学习网络内部执行预测编码。在PMCNN的基础上,我们进一步探索了一个基于学习的视频压缩框架,其中包含迭代分析/合成和二值化的额外组件。实验结果证明了该方案的有效性。虽然本文没有采用熵编码和复杂的配置,我们仍然表现出上级性能相比,MPEG-2和实现与H. 264编解码器的结果。提出的基于学习的方案提供了一个可能的新方向,以进一步提高压缩效率和未来的视频编码的功能。
One key challenge to learning-based video compression is that motion predictive coding, a very effective tool for video compression, can hardly be trained into a neural network. In this paper, we propose the concept of PixelMotionCNN (PMCNN) which includes motion extension and hybrid prediction networks. PMCNN can model spatiotemporal coherence to effectively perform predictive coding inside the learning network. On the basis of PMCNN, we further explore a learning-based framework for video compression with additional components of iterative analysis/synthesis and binarization. The experimental results demonstrate the effectiveness of the proposed scheme. Although entropy coding and complex configurations are not employed in this paper, we still demonstrate superior performance compared with MPEG-2 and achieve comparable results with H.264 codec. The proposed learning-based scheme provides a possible new direction to further improve compression efficiency and functionalities of future video coding.
DOI: --
发表时间: 2015-11
期刊: CoRR
影响因子: --
作者:
G. Toderici;Sean M. O'Malley;S. Hwang;Damien Vincent;David C. Minnen;S. Baluja;Michele Covell;
通讯作者: G. Toderici;Sean M. O'Malley;S. Hwang;Damien Vincent;David C. Minnen;S. Baluja;Michele Covell;
DOI: --
发表时间: 2015-11
期刊: CoRR
影响因子: --
作者:
Michaël Mathieu;C. Couprie;Yann LeCun
通讯作者: Michaël Mathieu;C. Couprie;Yann LeCun
DOI: --
发表时间: --
期刊: --
影响因子: --
作者:
通讯作者: --
DOI: 10.1016/j.jvcir.2004.12.002
发表时间: 2006-04-01
影响因子: 2.6
作者:
Chen, Zhibo;Xu, Jianfeng;Zheng, Junli
通讯作者: Zheng, Junli