{"title":"An Approximative and Semi-automated Method to Create MPEG-4 Compliant Human Face Models","authors":"Ákos Tóth, Roland Kunkli","doi":"10.14232/actacyb.23.4.2018.5","DOIUrl":null,"url":null,"abstract":"In this paper, we introduce our method to facilitate the process of creating an MPEG-4 compliant face model based on a simple 3D mesh. The presented method is semi-automatic, and the user needs to choose only a few points on the model as a preprocessing step. We use a cage based deformation technique to approximate an input model with a generic one which already contains the required MPEG-4 parameters. In the paper, we also show how the cage can be constructed to surround the model completely and be close enough to the head to get better deformation results. After these steps, the resulting model can be used in any MPEG-4 based facial animation player.","PeriodicalId":187125,"journal":{"name":"Acta Cybern.","volume":"70 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Acta Cybern.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.14232/actacyb.23.4.2018.5","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
In this paper, we introduce our method to facilitate the process of creating an MPEG-4 compliant face model based on a simple 3D mesh. The presented method is semi-automatic, and the user needs to choose only a few points on the model as a preprocessing step. We use a cage based deformation technique to approximate an input model with a generic one which already contains the required MPEG-4 parameters. In the paper, we also show how the cage can be constructed to surround the model completely and be close enough to the head to get better deformation results. After these steps, the resulting model can be used in any MPEG-4 based facial animation player.