首页> 外国专利> METHOD FOR GENERATING 3D AVATAR FROM 2D IMAGE ON MOBILE COMMUNICATION TERMINAL

METHOD FOR GENERATING 3D AVATAR FROM 2D IMAGE ON MOBILE COMMUNICATION TERMINAL

机译:在移动通信终端上从2D图像生成3D虚拟形象的方法

摘要

The present invention relates to a method for generating three-dimensional avatar, a two-dimensional moving image of a face that is in particular input converted into 3D images on the communication terminal, it relates to a method for generating a three-dimensional image of the avatar by. ; To this end, the present invention, the feature point coordinates on the inputted two-dimensional face image a first step and to transform the three-dimensional mesh standard avatar through the affine transformation (affine transform) to form a three-dimensional avatar mesh corresponding to the two-dimensional face image is set; The second step and for mapping the face image of a two-dimensional three-dimensional avatar mesh formed in said step; When the third step of mapping the three-dimensional mesh and the avatar of the two-dimensional face image from the phase matching generating three-dimensional face image, and normalizing it to a predetermined size; And is characterized in that a combination of avatar items selected by the user with the three-dimensional face image normalized by the steps of: a fourth step of generating a three-dimensional avatar.
机译:用于生成三维化身的方法技术领域本发明涉及一种用于生成三维化身,特别是在通信终端上被输入转换为3D图像的面部的二维运动图像的方法,涉及一种用于生成三维化身的三维图像的方法。头像。 ;为此,本发明首先在输入的二维面部图像上对特征点进行坐标处理,并通过仿射变换(仿射变换)对三维网格标准化身进行变换,以形成对应的三维化身网格。设置二维人脸图像;第二步,用于映射在所述步骤中形成的二维三维化身网格的人脸图像;第三步,从所述相位匹配中映射出二维人脸图像的三维网格和化身,生成三维人脸图像,并将其规格化为预定大小;并且其特征在于,由用户选择的化身项目与通过以下步骤归一化的三维面部图像的组合:生成三维化身的第四步骤。

著录项

  • 公开/公告号KR100629382B1

    专利类型

  • 公开/公告日2006-09-29

    原文格式PDF

  • 申请/专利权人

    申请/专利号KR20050003592

  • 发明设计人 조은미;

    申请日2005-01-14

  • 分类号G06T15;

  • 国家 KR

  • 入库时间 2022-08-21 21:22:52

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号