Time-consistency of disocclusion filling algorithms in Depth Image Based Rendering

Michael Schmeing, Xiaoyi Jiang
{"title":"Time-consistency of disocclusion filling algorithms in Depth Image Based Rendering","authors":"Michael Schmeing, Xiaoyi Jiang","doi":"10.1109/3DTV.2011.5877201","DOIUrl":null,"url":null,"abstract":"Depth Image Based Rendering (DIBR) is a technique to render virtual views from the video-plus-depth 3D scene representation. A common phenomenon in DIBR are disocclusions, i.e., unfilled areas that occur in the rendered views. The performance of disocclusion filling algorithms is usually only tested in terms of their ability of finding plausible fillings frame-by-frame. Time-consistency, however, is a crucial property in video processing. Missing time-consistency results in disturbing flicker artifacts. With our work, we want to point out the existence of this problem. We also introduce a measure to quantify the amount of flicker for a first study of this phenomenon.","PeriodicalId":158764,"journal":{"name":"2011 3DTV Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2011-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"20","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2011 3DTV Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/3DTV.2011.5877201","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 20

Abstract

Depth Image Based Rendering (DIBR) is a technique to render virtual views from the video-plus-depth 3D scene representation. A common phenomenon in DIBR are disocclusions, i.e., unfilled areas that occur in the rendered views. The performance of disocclusion filling algorithms is usually only tested in terms of their ability of finding plausible fillings frame-by-frame. Time-consistency, however, is a crucial property in video processing. Missing time-consistency results in disturbing flicker artifacts. With our work, we want to point out the existence of this problem. We also introduce a measure to quantify the amount of flicker for a first study of this phenomenon.
深度图像绘制中消光填充算法的时间一致性研究
基于深度图像的渲染(deep Image Based Rendering, DIBR)是一种基于视频加深度3D场景表示的虚拟视图渲染技术。在DIBR中常见的现象是咬合,即在渲染视图中出现的未填充区域。去咬合填充算法的性能通常只测试其逐帧寻找可信填充的能力。然而,时间一致性是视频处理中的一个关键特性。缺少时间一致性会导致令人不安的闪烁伪影。通过我们的工作,我们想指出这个问题的存在。我们还引入了一种量化闪烁量的方法来首次研究这一现象。
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