{"title":"A Virtual View Synthesis Algorithm Based on Image Inpainting","authors":"Huayang Wu, Jie Feng, Huaxiong Zhang, Qiankun Lv","doi":"10.1109/ICNDC.2012.44","DOIUrl":null,"url":null,"abstract":"The virtual view synthesis is a key technique in 3D video applications. In this paper, a new algorithm based on image in painting is proposed. Firstly, the depth image is processed by automatic segmentation to recognize the foreground and background. In order to reduce the big holes generated by view warping, in painting is processed on the edge between foreground and background according to the disparity. Then depth image based rendering(DIBR) is processed to foreground image. Finally the two generated images are merged to obtain the virtual view image. Experimental results show that the proposed method can obtain satisfactory rendering results.","PeriodicalId":151593,"journal":{"name":"2012 Third International Conference on Networking and Distributed Computing","volume":"80 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2012-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2012 Third International Conference on Networking and Distributed Computing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICNDC.2012.44","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2
Abstract
The virtual view synthesis is a key technique in 3D video applications. In this paper, a new algorithm based on image in painting is proposed. Firstly, the depth image is processed by automatic segmentation to recognize the foreground and background. In order to reduce the big holes generated by view warping, in painting is processed on the edge between foreground and background according to the disparity. Then depth image based rendering(DIBR) is processed to foreground image. Finally the two generated images are merged to obtain the virtual view image. Experimental results show that the proposed method can obtain satisfactory rendering results.