• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Pacific-Rim conference on multimedia >Convolutional Neural Network Based Inter-Frame Enhancement for 360-Degree Video Streaming
【24h】

Convolutional Neural Network Based Inter-Frame Enhancement for 360-Degree Video Streaming

机译：基于卷积神经网络的帧间增强用于360度视频流

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

360-degree video has attracted more and more attention in recent years. However, it is a highly challenging task to transmit the high-resolution video within the limited bandwidth. In this paper, we first propose to unequally compress the cubemaps in each frame of the 360-degree video to reduce the total bitrate of the transmitted data. Specifically, a Group of Pictures (GOP) is used as a unit to alternately transmit different versions of the video. Each version consists of 3 high-quality cubemaps and 3 low-quality cubemaps. Then, the convolutional neural network (CNN) is introduced to enhance the low-quality cubemaps with the high-quality cubemaps by exploring the inter-frame similarities. It is shown in the experiment that a single CNN model can be used for various videos. The experimental results also show that the proposed method has an excellent quality enhancement compared with the benchmark in terms of PSNR, especially for videos with slow motion.
机译：近年来，360度视频已引起越来越多的关注。但是，在有限的带宽内传输高分辨率视频是一项极富挑战性的任务。在本文中，我们首先提出在360度视频的每一帧中不均等地压缩立方体贴图，以减少传输数据的总比特率。具体来说，图片组（GOP）作为单位来交替传输视频的不同版本。每个版本均包含3个高质量的立方体贴图和3个低质量的立方体贴图。然后，引入卷积神经网络（CNN），通过探索帧间相似度，用高质量的立方体贴图增强低质量的立方体贴图。实验表明，单个CNN模型可用于各种视频。实验结果还表明，相对于基准而言，该方法在PSNR方面具有出色的质量增强，特别是对于慢动作视频。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号