Virtual view synthesis from uncalibrated stereo cameras

M. Akhloufi, V. Polotski, P. Cohen
{"title":"Virtual view synthesis from uncalibrated stereo cameras","authors":"M. Akhloufi, V. Polotski, P. Cohen","doi":"10.1109/MMCS.1999.778564","DOIUrl":null,"url":null,"abstract":"This paper presents a new approach to the synthesis of a novel view from two images captured by a non-calibrated stereo system. Here view synthesis employs epipolar constraints associated with a two camera configuration. A fundamental matrix is used to obtain features in the synthesized view via reprojection of corresponding features in the source images. Unlike classical methods which are based on inferring three dimensional structure of the scene or use dense correspondence between the source images to produce the new synthesized image, this method requires only sparse correspondence between source image features. Perspective image warping techniques then render the remaining image points via interpolation. The approach permits interactive view synthesis in: immersive telepresence systems, realistic virtual worlds and overlay of objects at different positions on live video of dynamic scenes for augmented reality display systems. Method efficiency is illustrated with examples of synthetic and real scenes.","PeriodicalId":408680,"journal":{"name":"Proceedings IEEE International Conference on Multimedia Computing and Systems","volume":"122 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1999-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings IEEE International Conference on Multimedia Computing and Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/MMCS.1999.778564","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5

Abstract

This paper presents a new approach to the synthesis of a novel view from two images captured by a non-calibrated stereo system. Here view synthesis employs epipolar constraints associated with a two camera configuration. A fundamental matrix is used to obtain features in the synthesized view via reprojection of corresponding features in the source images. Unlike classical methods which are based on inferring three dimensional structure of the scene or use dense correspondence between the source images to produce the new synthesized image, this method requires only sparse correspondence between source image features. Perspective image warping techniques then render the remaining image points via interpolation. The approach permits interactive view synthesis in: immersive telepresence systems, realistic virtual worlds and overlay of objects at different positions on live video of dynamic scenes for augmented reality display systems. Method efficiency is illustrated with examples of synthetic and real scenes.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
虚拟视图合成从未校准的立体摄像机
本文提出了一种从非校准立体系统捕获的两幅图像合成新视图的新方法。在这里,视图合成使用与双相机配置相关的极面约束。利用基本矩阵对源图像中的特征进行重投影,得到合成视图中的特征。与传统的基于推断场景三维结构或利用源图像之间的密集对应关系生成新的合成图像的方法不同,该方法只需要源图像特征之间的稀疏对应关系。透视图像扭曲技术,然后渲染剩余的图像点通过插值。该方法允许交互式视图合成:沉浸式远程呈现系统,逼真的虚拟世界以及在增强现实显示系统的动态场景实时视频上不同位置的物体叠加。通过合成场景和真实场景的实例说明了方法的有效性。
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 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
A fast H.261 software codec for high quality videoconferencing on PCs Virtual European School-VES An adaptive transport service for multimedia streams Virtual social clubs: meeting places for the Internet community An investigation of audio-visual speech recognition as applied to multimedia speech therapy applications
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1