{"title":"Enhanced Multiple Local Ray-spaces Method for Walk-through View Synthesis","authors":"M. P. Tehrani, A. Ishikawa, S. Sakazawa, A. Koike","doi":"10.1109/ISUC.2008.12","DOIUrl":null,"url":null,"abstract":"In this paper, we propose geometry based image-based rendering method for sparse multicamera system using multiple local ray-space representation and 3D model generation. In this system, the quality of walk-through view experience is impaired by inaccurate camera parameters and 3D model. In order to eliminate these affects, we enhance the reconstructed local ray-spaces using stereo matching approach. Hence, free viewpoint rendering quality is improved significantly for walk-through image synthesis. Experimental results for several multiview sequences verify the effectiveness of our approach.","PeriodicalId":339811,"journal":{"name":"2008 Second International Symposium on Universal Communication","volume":"75 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2008-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2008 Second International Symposium on Universal Communication","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISUC.2008.12","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
In this paper, we propose geometry based image-based rendering method for sparse multicamera system using multiple local ray-space representation and 3D model generation. In this system, the quality of walk-through view experience is impaired by inaccurate camera parameters and 3D model. In order to eliminate these affects, we enhance the reconstructed local ray-spaces using stereo matching approach. Hence, free viewpoint rendering quality is improved significantly for walk-through image synthesis. Experimental results for several multiview sequences verify the effectiveness of our approach.