利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

30 条记录 (耗时 0.019 秒)

    Method for tracking head motion for 3D facial model animation from video stream
    3.
    发明申请
    Method for tracking head motion for 3D facial model animation from video stream 审中-公开
    用于从视频流追踪3D面部模型动画的头部运动的方法

    公开(公告)号：US20090153569A1

    公开(公告)日：2009-06-18

    申请号：US12314859

    申请日：2008-12-17

    申请人： Jeung Chul Park ,  Seong Jae Lim ,  Chang Woo Chu ,  Ho Won Kim ,  Ji Young Park ,  Bon Ki Koo

    发明人： Jeung Chul Park ,  Seong Jae Lim ,  Chang Woo Chu ,  Ho Won Kim ,  Ji Young Park ,  Bon Ki Koo

    IPC分类号： G06T15/70 ,  G06K9/00

    CPC分类号： G06T13/40 ,  G06K2009/3291 ,  G06T7/251 ,  G06T7/277 ,  G06T2207/10016 ,  G06T2207/30201

    摘要： A head motion tracking method for three-dimensional facial model animation, the head motion tracking method includes acquiring initial facial motion to be fit to an image of a three-dimensional model from an image inputted by a video camera; creating a silhouette of the three-dimensional model and projecting the silhouette; matching the silhouette created from the three-dimensional model with a silhouette acquired by a statistical feature point tracking scheme; and obtaining a motion parameter for the image of the three-dimensional model through motion correction using a texture to perform three-dimensional head motion tracking. In accordance with the present invention, natural three-dimensional facial model animation based on a real image acquired with a video camera can be performed automatically, thereby reducing time and cost.

    摘要翻译： 一种用于三维面部模型动画的头部运动跟踪方法，所述头部运动跟踪方法包括从由摄像机输入的图像获取拟合到三维模型的图像的初始面部运动; 创建三维模型的轮廓并投影轮廓; 将由三维模型创建的轮廓与通过统计特征点跟踪方案获取的轮廓相匹配; 并且通过使用纹理的运动校正来获得三维模型的图像的运动参数，以执行三维头部运动跟踪。 根据本发明，可以自动执行基于用摄像机获取的真实图像的自然三维面部模型动画，从而减少时间和成本。

    Method for automatic rigging and shape surface transfer of 3D standard mesh model based on muscle and nurbs by using parametric control
    5.
    发明授权
    Method for automatic rigging and shape surface transfer of 3D standard mesh model based on muscle and nurbs by using parametric control 有权
    通过参数控制，基于肌肉和鼻梁的3D标准网格模型的自动索引和形状表面传递方法

    公开(公告)号：US08610710B2

    公开(公告)日：2013-12-17

    申请号：US12970008

    申请日：2010-12-16

    申请人： Seong Jae Lim ,  Ho Won Kim ,  Han Byul Joo ,  Bon Ki Koo

    发明人： Seong Jae Lim ,  Ho Won Kim ,  Han Byul Joo ,  Bon Ki Koo

    IPC分类号： G06T15/00

    CPC分类号： G06T13/40

    摘要： Provided is a method for automatic rigging and shape surface transfer of a 3-D standard mesh model based on muscles and Nurbs by using parametric control. In some embodiments, the method includes: extracting a joint-skeleton structure from scan data of dynamic objects having a skeleton structure, or input 3-D mesh models, generating a muscle and an appearance surface based on anatomy information, and generating a standard mesh model that approximates the appearance of the dynamic objects by using the joint-skeleton structure and the generated muscle and appearance surface; and performing the shape surface transfer of the standard mesh model by comparing multi-view image information of the dynamic objects with projection image information of the standard mesh model.

    摘要翻译： 提供了一种通过使用参数控制，基于肌肉和Nurbs的3-D标准网格模型的自动索具和形状表面传递的方法。 在一些实施例中，该方法包括：从具有骨架结构的动态对象的扫描数据或基于解剖信息生成肌肉和外观表面的输入3-D网格模型提取关节骨架结构，以及生成标准网格 通过使用关节骨架结构和产生的肌肉和外观表面近似动态对象的外观的模型; 并通过将动态对象的多视点图像信息与标准网格模型的投影图像信息进行比较来执行标准网格模型的形状表面传送。