Inter-prediction optimisations for fast HEVC encoding of ultra high definition content

Ivan Zupancic, Saverio G. Blasi, E. Izquierdo
{"title":"Inter-prediction optimisations for fast HEVC encoding of ultra high definition content","authors":"Ivan Zupancic, Saverio G. Blasi, E. Izquierdo","doi":"10.1109/IWSSIP.2015.7314183","DOIUrl":null,"url":null,"abstract":"Thanks to technological advances in devices for video signal capturing and displaying, the usage of large resolution video formats is becoming more and more popular in consumer and professional applications. The new Ultra High Definition (UHD) format aims to provide enhanced viewing experience with its spatial resolution of at least 3840 × 2160 luma samples per frame and temporal resolution of up to 120 frames per second. Such a large amount of raw data requires extremely high levels of compression efficiency. The latest state-of-the-art High Efficiency Video Coding (HEVC) standard was developed also to respond to these needs. HEVC outperforms previous video coding standards in terms of coding efficiency, especially while encoding high resolution video content. However, this comes at very high computational costs, making current HEVC encoder implementations of very limited usage. In this paper, a fast inter-prediction scheme is proposed targeting fast mode decision based on reverse Coding Unit (CU) visiting order, and early termination of both the integer- and fractional-pel motion estimation processes. Experimental results show that the proposed algorithm achieves on average 72.9% time savings, for limited coding losses.","PeriodicalId":249021,"journal":{"name":"2015 International Conference on Systems, Signals and Image Processing (IWSSIP)","volume":"206 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2015 International Conference on Systems, Signals and Image Processing (IWSSIP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IWSSIP.2015.7314183","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 4

Abstract

Thanks to technological advances in devices for video signal capturing and displaying, the usage of large resolution video formats is becoming more and more popular in consumer and professional applications. The new Ultra High Definition (UHD) format aims to provide enhanced viewing experience with its spatial resolution of at least 3840 × 2160 luma samples per frame and temporal resolution of up to 120 frames per second. Such a large amount of raw data requires extremely high levels of compression efficiency. The latest state-of-the-art High Efficiency Video Coding (HEVC) standard was developed also to respond to these needs. HEVC outperforms previous video coding standards in terms of coding efficiency, especially while encoding high resolution video content. However, this comes at very high computational costs, making current HEVC encoder implementations of very limited usage. In this paper, a fast inter-prediction scheme is proposed targeting fast mode decision based on reverse Coding Unit (CU) visiting order, and early termination of both the integer- and fractional-pel motion estimation processes. Experimental results show that the proposed algorithm achieves on average 72.9% time savings, for limited coding losses.
超高清内容的快速HEVC编码的预测间优化
由于视频信号捕获和显示设备的技术进步,大分辨率视频格式的使用在消费者和专业应用中越来越受欢迎。新的超高清(UHD)格式旨在提供增强的观看体验,其空间分辨率至少为每帧3840 × 2160亮度样本,时间分辨率高达每秒120帧。如此大量的原始数据需要极高的压缩效率。最新的最先进的高效视频编码(HEVC)标准也是为了满足这些需求而开发的。HEVC在编码效率方面优于以往的视频编码标准,特别是在编码高分辨率视频内容时。然而,这带来了很高的计算成本,使得当前HEVC编码器的使用非常有限。本文提出了一种基于反向编码单元(CU)访问顺序、整数运动估计过程和分数运动估计过程提前终止的快速模式决策互预测方案。实验结果表明,在编码损失有限的情况下,该算法平均节省了72.9%的时间。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信