Optimal depth recovery using image guided TGV with depth confidence for high-quality view synthesis.pdfVIP

下载本文档

10
0
约6.95万字
约 16页
2017-03-16 发布于天津
举报
版权申诉

Optimal depth recovery using image guided TGV with depth confidence for high-quality view synthesis.pdf

1、本文档共16页，可阅读全部内容。
2、原创力文档（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。
3、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。
4、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)。
5、该文档为VIP文档，如果想要下载，成为VIP会员后，下载免费。
6、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。
7、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。
8、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

Optimal depth recovery using image guided TGV with depth confidence for high-quality view synthesis.pdf

J. Vis. Commun. Image R. 39 (2016) 24–39 Contents lists available at ScienceDirect J. Vis. Commun. Image R. journal homepage: /locate/jvci Optimal depth recovery using image guided TGV with depth con?dence for high-quality view synthesis Pongsak Lasang a,b,?, Wuttipong Kumwilaisak c, Yazhou Liu d, Sheng Mei Shen a a Core Technology Group, Panasonic RD Center Singapore, Singapore b Department of Computer Engineering, King Mongkut′s University of Technology Thonburi, Bangkok, Thailand c Department of Electronics and Telecommunication Engineering, King Mongkut′s University of Technology Thonburi, Bangkok, Thailand d Department of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210048, China article info Article history: Received 27 May 2015 Revised 13 April 2016 Accepted 10 May 2016 Available online 12 May 2016 Keywords: RGB-D sensors Depth con?dence Depth recovery Depth Image Based Rendering (DIBR) View synthesis Hole ?lling abstract This paper presents a new depth image recovery method for RGB-D sensors giving a complete, sharp, and accurate object shape from a noisy boundary depth map. The proposed method uses the image guided Total Generalized Variation (TGV) with the depth con?dence. A new directional hole ?lling method of view synthesis is also investigated to produce natural texture in hole regions whereas reducing blurring effect and preventing distortion. Thus, a high-quality image view can be achieved. Experimental results show that the proposed method yields higher quality recovered depth maps and synthesized image views than other previous methods. ó 2016 Elsevier Inc. All rights reserved. 1. Introduction A RGB-D sensor is one of the fundamental sensing devices and plays an essential role in many vision processing applications. It can capture both visual texture and geometrical structure information of a scene. With the rapid development of sensor technologies and a great invention of Kinect’s sensor [1], a real-time