Won-Sook Lee, M. Escher, Gaël Sannier, N. Magnenat-Thalmann
{"title":"MPEG-4 compatible faces from orthogonal photos","authors":"Won-Sook Lee, M. Escher, Gaël Sannier, N. Magnenat-Thalmann","doi":"10.1109/CA.1999.781211","DOIUrl":null,"url":null,"abstract":"MPEG-4 is scheduled to become an international standard in March 1999. The paper demonstrates an experiment for a virtual cloning method and animation system, which is compatible with the MPEG-4 standard facial object specification. Our method uses orthogonal photos (front and side view) as input and reconstructs the 3D facial model. The method is based on extracting MPEG-4 face definition parameters (FDP) from photos, which initializes a custom face in a more capable interface, and deforming a generic model. Texture mapping is employed using an image composed of the two orthogonal images, which is done completely automatically. A reconstructed head can be animated immediately inside our animation system, which is adapted to the MPEG-4 standard specification of face animation parameters (FAP). The result is integrated into our virtual human director (VHD) system.","PeriodicalId":108994,"journal":{"name":"Proceedings Computer Animation 1999","volume":"458 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1999-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"78","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings Computer Animation 1999","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CA.1999.781211","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 78
Abstract
MPEG-4 is scheduled to become an international standard in March 1999. The paper demonstrates an experiment for a virtual cloning method and animation system, which is compatible with the MPEG-4 standard facial object specification. Our method uses orthogonal photos (front and side view) as input and reconstructs the 3D facial model. The method is based on extracting MPEG-4 face definition parameters (FDP) from photos, which initializes a custom face in a more capable interface, and deforming a generic model. Texture mapping is employed using an image composed of the two orthogonal images, which is done completely automatically. A reconstructed head can be animated immediately inside our animation system, which is adapted to the MPEG-4 standard specification of face animation parameters (FAP). The result is integrated into our virtual human director (VHD) system.