An efficient depth image-based rendering with depth reliability maps for view synthesis.pdfVIP

下载本文档

17
0
约4.16万字
约 9页
2017-03-16 发布于天津
举报
版权申诉

An efficient depth image-based rendering with depth reliability maps for view synthesis.pdf

1、有哪些信誉好的足球投注网站（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。。
2、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击这里二次下载。
3、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。
4、该文档为VIP文档，如果想要下载，成为VIP会员后，下载免费。
5、成为VIP后，下载本文档将扣除1次下载权益。下载后，不支持退款、换文档。如有疑问请联系我们。
6、成为VIP后，您将拥有八大权益，权益包括：VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
7、VIP文档为合作方或网友上传，每下载1次，网站将根据用户上传文档的质量评分、类型等，对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档

An efficient depth image-based rendering with depth reliability maps for view synthesis.pdf

J. Vis. Commun. Image R. 41 (2016) 176–184 Contents lists available at ScienceDirect J. Vis. Commun. Image R. journal homepage: /locate/jvci An ef?cient depth image-based rendering with depth reliability maps for view synthesis q Yi Lai a,?, Xuguang Lan b, Yuehu Liu b, Nanning Zheng b a School of Telecommunication and Information Engineering, Xi’an University of Posts and Telecommunications, Xi’an 710121, PR China b Institute of Arti?cial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an 710049, PR China article info Article history: Received 21 June 2016 Revised 22 August 2016 Accepted 28 September 2016 Available online 29 September 2016 Keywords: Depth image-based rendering Depth reliability maps Interpolation weight View synthesis abstract In this paper, an ef?cient depth image-based rending (DIBR) with depth reliability maps (DRM) is proposed to improve the quality of synthesized images. First, a DRM-based occlusion-aware approach is developed to obtain a segmentation mask, which can explicitly indicate where the information in an intermediate image should be blended preferably. Next, an improved weight model for view creation is introduced to enhance the quality of synthesized images. Finally, a distance and depth-based subpixel weighted (DDSPW) algorithm is presented to solve the visibility and resampling problems. Experimental results demonstrate that the treated DIBR schemes have better performance for view synthesis than the other three methods through the subjective visual perception and objective assessments in terms of peak signal to noise ratio and structural similarity index. ó 2016 Elsevier Inc. All rights reserved. 1. Introduction Three dimensional video (3DV) has gained considerable attention in consumer market due to the progress of digital video compression, 3D display, and computer vision algorithms [1,2]. A key technique for rendering arbitrary views of a scene of 3DV is view synthesis. View synthesis is the process of combining a set