T. Barrios, Cédric Niquin, S. Prévost, P. Souchet, C. Loscos
{"title":"A wide-baseline multiview system for indoor scene capture","authors":"T. Barrios, Cédric Niquin, S. Prévost, P. Souchet, C. Loscos","doi":"10.1145/3565516.3565518","DOIUrl":null,"url":null,"abstract":"We present a complete multiview acquisition system, a camera array allowing depth reconstruction based on disparity. We built a new wide-baseline camera grid supported by an interactive camera controller purposely built for indoor large scene capture. It is composed of 16 cameras aligned as a 4 × 4 grid, synchronized, and characterized. The design of the camera system manages storage and real-time capture viewing. We also propose a DNN-based approach to estimate the floating-point disparity values, which is adapted to wide-baseline configurations while providing high precision, even for sharp and concave objects. The ultimate result is a dense 3D point cloud which offers versatile possibilities of viewing.","PeriodicalId":367303,"journal":{"name":"Proceedings of the 19th ACM SIGGRAPH European Conference on Visual Media Production","volume":"213 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 19th ACM SIGGRAPH European Conference on Visual Media Production","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3565516.3565518","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
We present a complete multiview acquisition system, a camera array allowing depth reconstruction based on disparity. We built a new wide-baseline camera grid supported by an interactive camera controller purposely built for indoor large scene capture. It is composed of 16 cameras aligned as a 4 × 4 grid, synchronized, and characterized. The design of the camera system manages storage and real-time capture viewing. We also propose a DNN-based approach to estimate the floating-point disparity values, which is adapted to wide-baseline configurations while providing high precision, even for sharp and concave objects. The ultimate result is a dense 3D point cloud which offers versatile possibilities of viewing.