Convolutional Neural Network for Intermediate View Enhancement in Multiview Streaming
Convolutional Neural Network for Intermediate View Enhancement in Multiview Streaming
复制标题
用于多视图流媒体中中间视图增强的卷积神经网络
DOI：
10.1109/tmm.2017.2726900
复制
发表时间：
2018
影响因子：
7.3
通讯作者：
Marco Grangetto
中科院分区：
文献类型：
--
作者：
Li Yu;Tammam Tillo;Jimin Xiao;Marco Grangetto
多视图视频流继续受到欢迎，因为它提供了良好的观看体验，以及通过增加的网络吞吐量和其他最近的技术发展实现的可用性。用户对交互式多视频流的需求也在增加，这种视频流可以根据要求提供无缝的视图切换。然而，如何在带宽限制下实现实时场景导航的稳定、高质量视频流是一项极具挑战性的任务。本文提出了一种卷积神经网络辅助的无缝多视频流系统来解决这一问题。本文提出的方法从两个角度解决了这一问题。首先，提出了一种基于卷积神经网络的多视图表示方法，该方法在不影响多视图视频压缩效率的前提下提供了灵活的交互性。其次，提出了一种以导航模型为指导的比特分配机制，在提供无缝导航的同时适应网络带宽的波动。这两个模块紧密配合，为用户提供优化的观看体验。它们可以集成到任何现有的多视频流框架中，以提高整体性能。实验结果证明了该方法在多视点无缝流传输中的有效性。
Multiview video streaming continues to gain popularity due to the great viewing experience it offers, as well as its availability that has been enabled by increased network throughput and other recent technical developments. User demand for interactive multiview video streaming that provides seamless view switching upon request is also increasing. However, it is a highly challenging task to stream stable and high quality videos that allow real-time scene navigation within the bandwidth constraint. In this paper, a convolutional neural network (ConvNet)-assisted seamless multiview video streaming system is proposed to tackle the challenge. The proposed method solves the problem from two perspectives. First, a ConvNet-assisted multiview representation method is proposed, which provides flexible interactivity without compromising on multiview video compression efficiency. Second, a bit allocation mechanism guided by a navigation model is developed to provide seamless navigation and adapt to network bandwidth fluctuations at the same time. These two blocks work closely to provide an optimized viewing experience to users. They can be integrated into any existing multiview video streaming framework to enhance overall performance. Experimental results demonstrate the effectiveness of the proposed method for seamless multiview streaming.
登录
查看更多内容
DOI：
10.1109/icspcs.2014.7021071
发表时间：
2014-12
期刊：
2014 8th International Conference on Signal Processing and Communication Systems (ICSPCS)
影响因子：
--
作者：
Tianyu Su;A. Javadtalab;A. Yassine;S. Shirmohammadi
通讯作者：
Tianyu Su;A. Javadtalab;A. Yassine;S. Shirmohammadi
DOI：
10.1007/978-3-319-24078-7_41
发表时间：
2015-09
期刊：
--
影响因子：
--
作者：
Jimin Xiao;M. Hannuksela;T. Tillo;M. Gabbouj
通讯作者：
Jimin Xiao;M. Hannuksela;T. Tillo;M. Gabbouj
DOI：
10.1109/icip.2011.6116618
发表时间：
2011-12
期刊：
2011 18th IEEE International Conference on Image Processing
影响因子：
--
作者：
Thomas Maugey;P. Frossard
通讯作者：
Thomas Maugey;P. Frossard
DOI：
10.1109/vcip.2014.7051491
发表时间：
2014-12
期刊：
2014 IEEE Visual Communications and Image Processing Conference
影响因子：
--
作者：
Yanping Zhou;Y. Duan;Jun Sun;Zongming Guo
通讯作者：
Yanping Zhou;Y. Duan;Jun Sun;Zongming Guo
DOI：
10.1016/j.image.2013.01.006
发表时间：
2011-12
期刊：
2011 4th International Congress on Image and Signal Processing
影响因子：
--
作者：
Ci Wang;Jun Zhou;Shu Liu
通讯作者：
Ci Wang;Jun Zhou;Shu Liu