Pan Ling-jiao, Zhu You-lian, Qian Zhi-wen, Chen Qin, Hong Yue
{"title":"Real-time virtual view synthesis based on GPU parallel programming","authors":"Pan Ling-jiao, Zhu You-lian, Qian Zhi-wen, Chen Qin, Hong Yue","doi":"10.1109/CCDC.2015.7162566","DOIUrl":null,"url":null,"abstract":"To generate a virtual view image in real-time, this paper propose a fast depth image based rendering method. Firstly, a simple and efficient hole filling method is performed to prevent hole filling error and improve virtual view quality. Secondly, high speed GPU is used to speed up computation speed of DIBR algorithm. Simulation results show that the proposed approach can generate virtual view images 10 times faster than a CPU-based processing. The proposed method not only takes small bandwidth but also achieves good view quality subjectively. It can be applied to real time 3DTV system.","PeriodicalId":273292,"journal":{"name":"The 27th Chinese Control and Decision Conference (2015 CCDC)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"The 27th Chinese Control and Decision Conference (2015 CCDC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CCDC.2015.7162566","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3
Abstract
To generate a virtual view image in real-time, this paper propose a fast depth image based rendering method. Firstly, a simple and efficient hole filling method is performed to prevent hole filling error and improve virtual view quality. Secondly, high speed GPU is used to speed up computation speed of DIBR algorithm. Simulation results show that the proposed approach can generate virtual view images 10 times faster than a CPU-based processing. The proposed method not only takes small bandwidth but also achieves good view quality subjectively. It can be applied to real time 3DTV system.