基于外观的虚拟视图生成的时间变化事件从多相机图像在3D房间

Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062) Pub Date : 1999-10-04 DOI:10.1109/IM.1999.805384

H. Saito, Shigeyuki Baba, M. Kimura, S. Vedula, T. Kanade

{"title":"基于外观的虚拟视图生成的时间变化事件从多相机图像在3D房间","authors":"H. Saito, Shigeyuki Baba, M. Kimura, S. Vedula, T. Kanade","doi":"10.1109/IM.1999.805384","DOIUrl":null,"url":null,"abstract":"We present an \"appearance based\" virtual view generation method for temporally-varying events taken by multiple cameras of the \"3D Room\", developed by our group. With this method we can generate images from any virtual view point between two selected real views. The virtual appearance view generation method is based on simple interpolation between two selected views. The correspondence between the views are automatically generated from the multiple images by use of the volumetric model shape reconstruction framework. Since the correspondences are obtained by the recovered volumetric model, even occluded regions in the views can be correctly interpolated in the virtual view images. The virtual view image sequences are presented for demonstrating the performance of the virtual view image generation in the 3D Room.","PeriodicalId":110347,"journal":{"name":"Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1999-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"69","resultStr":"{\"title\":\"Appearance-based virtual view generation of temporally-varying events from multi-camera images in the 3D room\",\"authors\":\"H. Saito, Shigeyuki Baba, M. Kimura, S. Vedula, T. Kanade\",\"doi\":\"10.1109/IM.1999.805384\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We present an \\\"appearance based\\\" virtual view generation method for temporally-varying events taken by multiple cameras of the \\\"3D Room\\\", developed by our group. With this method we can generate images from any virtual view point between two selected real views. The virtual appearance view generation method is based on simple interpolation between two selected views. The correspondence between the views are automatically generated from the multiple images by use of the volumetric model shape reconstruction framework. Since the correspondences are obtained by the recovered volumetric model, even occluded regions in the views can be correctly interpolated in the virtual view images. The virtual view image sequences are presented for demonstrating the performance of the virtual view image generation in the 3D Room.\",\"PeriodicalId\":110347,\"journal\":{\"name\":\"Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062)\",\"volume\":\"11 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1999-10-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"69\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/IM.1999.805384\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IM.1999.805384","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 69

摘要

我们提出了一种“基于外观”的虚拟视图生成方法，用于由我们小组开发的“3D房间”的多个摄像机拍摄的时间变化事件。使用这种方法，我们可以从两个选定的真实视图之间的任何虚拟视点生成图像。虚拟外观视图生成方法是基于两个选定视图之间的简单插值。利用体模型形状重构框架，从多幅图像中自动生成视图之间的对应关系。由于对应关系是由恢复的体模型获得的，因此即使视图中的遮挡区域也可以正确地插值到虚拟视图图像中。为了演示虚拟视图图像生成在3D房间中的性能，给出了虚拟视图图像序列。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Appearance-based virtual view generation of temporally-varying events from multi-camera images in the 3D room

We present an "appearance based" virtual view generation method for temporally-varying events taken by multiple cameras of the "3D Room", developed by our group. With this method we can generate images from any virtual view point between two selected real views. The virtual appearance view generation method is based on simple interpolation between two selected views. The correspondence between the views are automatically generated from the multiple images by use of the volumetric model shape reconstruction framework. Since the correspondences are obtained by the recovered volumetric model, even occluded regions in the views can be correctly interpolated in the virtual view images. The virtual view image sequences are presented for demonstrating the performance of the virtual view image generation in the 3D Room.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062)

自引率

0.00%

发文量