Sarah Fachada, Daniele Bonatto, Yupeng Xie, Patrice Rondao-Alface, Mehrdad Teratani, G. Lafruit
{"title":"Depth Image-Based Rendering of Non-Lambertian Content in MPEG Immersive Video","authors":"Sarah Fachada, Daniele Bonatto, Yupeng Xie, Patrice Rondao-Alface, Mehrdad Teratani, G. Lafruit","doi":"10.1109/IC3D53758.2021.9687263","DOIUrl":null,"url":null,"abstract":"In the context of the development of MPEG-I standard for immersive video compression ISO/IEC 23090-12 (MIV), the need of handling scenes with non-Lambertian materials arose. This class of material is omnipresent in natural scenes, but violates all the assumptions on which depth image-based rendering (DIBR) is based. In this paper, we present a view-synthesizer designed to handle non-Lambertian objects with DIBR, replacing the classical depth maps by multi-coefficients non-Lambertian maps. We report the results of the exploration experiments on Future MIV designed to test this rendering method against the classical DIBR approaches, and demonstrate promising results on all the tested sequences.","PeriodicalId":382937,"journal":{"name":"2021 International Conference on 3D Immersion (IC3D)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 International Conference on 3D Immersion (IC3D)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IC3D53758.2021.9687263","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
In the context of the development of MPEG-I standard for immersive video compression ISO/IEC 23090-12 (MIV), the need of handling scenes with non-Lambertian materials arose. This class of material is omnipresent in natural scenes, but violates all the assumptions on which depth image-based rendering (DIBR) is based. In this paper, we present a view-synthesizer designed to handle non-Lambertian objects with DIBR, replacing the classical depth maps by multi-coefficients non-Lambertian maps. We report the results of the exploration experiments on Future MIV designed to test this rendering method against the classical DIBR approaches, and demonstrate promising results on all the tested sequences.