Method of creating animatable digital clone from multi-view images
    5.
    发明授权
    Method of creating animatable digital clone from multi-view images 失效
    从多视图图像创建可动画数字克隆的方法

    公开(公告)号:US08712146B2

    公开(公告)日:2014-04-29

    申请号:US12612792

    申请日:2009-11-05

    CPC分类号: G06T13/40

    摘要: The present invention relates to a method of creating an animatable digital clone includes receiving input multi-view images of an actor captured by at least two cameras and reconstructing a three-dimensional appearance therefrom, accepting shape information selectively based on a probability of photo-consistency in the input multi-view images obtained from the reconstruction and transferring a mesh topology of a reference human body model onto a shape of the actor obtained from the reconstruction. The method further includes generating an initial human body model of the actor via transfer of the mesh topology utilizing sectional shape information of the actor's joints, and generating a genuine human body model of the actor from learning genuine behavioral characteristics of the actor by applying the initial human body model to multi-view posture learning images where performance of a predefined motion by the actor is recorded.

    摘要翻译: 本发明涉及一种创建可动画数字克隆的方法,包括:接收由至少两个相机拍摄的演员的输入多视图图像,并从其重构三维外观,基于光一致性的概率有选择地接受形状信息 在从重构获得的输入多视图图像中,并将参考人体模型的网格拓扑转移到从重建获得的运动员的形状上。 该方法还包括通过使用演员关节的截面形状信息的网格拓扑的传递来生成演员的初始人体模型,以及通过应用初始的演员生成演员的真正的人体模型来学习演员的真实行为特征 人体模型以多视角姿态学习图像,其中记录由演员执行预定义的运动。

    METHOD AND APPARATUS FOR IMPLEMENTING MOTION CONTROL CAMERA EFFECT BASED ON SYNCHRONIZED MULTI-IMAGES
    9.
    发明申请
    METHOD AND APPARATUS FOR IMPLEMENTING MOTION CONTROL CAMERA EFFECT BASED ON SYNCHRONIZED MULTI-IMAGES 审中-公开
    基于同步多图像实现运动控制相机效果的方法和装置

    公开(公告)号:US20100157022A1

    公开(公告)日:2010-06-24

    申请号:US12495169

    申请日:2009-06-30

    IPC分类号: H04N13/02

    摘要: A method of implementing a motion control camera effect includes: inputting images of an object captured at one or more points of view; inputting a control parameter containing a motion control camera effect to be applied to the input images, a target time of the motion control camera effect, and a reproducing speed; extracting frames of the target time from the input images; processing the frames using software based on the control parameter; and outputting the processed frames at the reproducing speed. The motion control camera effect includes at least one of a motion control camera effect for a fixed viewpoint still object, a motion control camera effect for a fixed viewpoint moving object, a motion control camera effect for a free viewpoint still object, a motion control camera effect for a free viewpoint moving object, and a dual motion control camera effect.

    摘要翻译: 实现运动控制相机效果的方法包括:输入在一个或多个观点拍摄的对象的图像; 输入包含要施加到输入图像的运动控制相机效果的控制参数,运动控制相机效果的目标时间和再现速度; 从输入图像提取目标时间的帧; 使用基于控制参数的软件处理帧; 并以再现速度输出处理后的帧。 运动控制相机效果包括用于固定视点静止物体的运动控制相机效果,固定视点移动物体的运动控制相机效果,自由视点静止物体的运动控制相机效果,运动控制相机 对于自由视点运动物体的效果,以及双运动控制相机效果。

    METHOD OF CREATING ANIMATABLE DIGITAL CLONE FROM MULTI-VIEW IMAGES
    10.
    发明申请
    METHOD OF CREATING ANIMATABLE DIGITAL CLONE FROM MULTI-VIEW IMAGES 失效
    从多视图创建动画数字克隆的方法

    公开(公告)号:US20100158354A1

    公开(公告)日:2010-06-24

    申请号:US12612792

    申请日:2009-11-05

    IPC分类号: G06K9/00

    CPC分类号: G06T13/40

    摘要: The present invention relates to a method of creating an animatable digital clone includes receiving input multi-view images of an actor captured by at least two cameras and reconstructing a three-dimensional appearance therefrom, accepting shape information selectively based on a probability of photo-consistency in the input multi-view images obtained from the reconstruction and transferring a mesh topology of a reference human body model onto a shape of the actor obtained from the reconstruction. The method further includes generating an initial human body model of the actor via transfer of the mesh topology utilizing sectional shape information of the actor's joints, and generating a genuine human body model of the actor from learning genuine behavioral characteristics of the actor by applying the initial human body model to multi-view posture learning images where performance of a predefined motion by the actor is recorded.

    摘要翻译: 本发明涉及一种创建可动画数字克隆的方法,包括:接收由至少两个相机拍摄的演员的输入多视图图像,并从其重构三维外观,基于光一致性的概率有选择地接受形状信息 在从重构获得的输入多视图图像中,并将参考人体模型的网格拓扑转移到从重建获得的运动员的形状上。 该方法还包括通过使用演员关节的截面形状信息的网格拓扑的传递来生成演员的初始人体模型,以及通过应用初始的演员生成演员的真正的人体模型来学习演员的真实行为特征 人体模型以多视角姿态学习图像,其中记录由演员执行预定义的运动。