SYSTEM AND METHOD FOR AVATAR GENERATION, RENDERING AND ANIMATION
    2.
    发明申请
    SYSTEM AND METHOD FOR AVATAR GENERATION, RENDERING AND ANIMATION 审中-公开
    用于产生,渲染和动画的系统和方法

    公开(公告)号:US20140198121A1

    公开(公告)日:2014-07-17

    申请号:US13997265

    申请日:2012-04-09

    IPC分类号: G06T11/60

    CPC分类号: G06T11/60 H04N7/157

    摘要: A video communication system that replaces actual live images of the participating users with animated avatars. The system allows generation, rendering and animation of a two-dimensional (2-D) avatar of a user's face. The 2-D avatar represents a user's basic face shape and key facial characteristics, including, but not limited to, position and shape of the eyes, nose, mouth, and face contour. The system further allows adaptive rendering for displaying allow different scales of the 2-D avatar to be displayed on associated different sized displays of user devices.

    摘要翻译: 视频通信系统,用动画头像代替参与用户的实际实况图像。 该系统允许用户脸部的二维(2-D)头像的生成,呈现和动画。 2-D头像表示用户的基本面部形状和关键面部特征,包括但不限于眼睛,鼻子,嘴巴和脸部轮廓的位置和形状。 该系统进一步允许用于显示的自适应渲染,允许在用户设备的相关联的不同大小的显示器上显示不同比例的2-D化身。

    PARAMETERIZED 3D FACE GENERATION
    4.
    发明申请
    PARAMETERIZED 3D FACE GENERATION 审中-公开
    参数化3D面产生

    公开(公告)号:US20130271451A1

    公开(公告)日:2013-10-17

    申请号:US13976869

    申请日:2011-08-09

    IPC分类号: G06T17/00

    CPC分类号: G06T17/00

    摘要: Systems, devices and methods are described including receiving a semantic description and associated measurement criteria for a facial control parameter, obtaining principal component analysis (PCA) coefficients, generating 3D faces in response to the PCA coefficients, determining a measurement value for each of the 3D faces based on the measurement criteria, and determining a regression parameters for the facial control parameter based on the measurement values.

    摘要翻译: 描述了系统,设备和方法,包括接收面部控制参数的语义描述和相关联的测量标准,获得主成分分析(PCA)系数,响应于PCA系数生成3D面,确定3D中每一个的测量值 基于测量标准的面部,以及基于测量值确定面部控制参数的回归参数。

    ADAPTIVE FACIAL EXPRESSION CALIBRATION
    8.
    发明申请
    ADAPTIVE FACIAL EXPRESSION CALIBRATION 有权
    自适应表情表达式校准

    公开(公告)号:US20140267413A1

    公开(公告)日:2014-09-18

    申请号:US13976039

    申请日:2013-03-14

    IPC分类号: G06T19/00

    摘要: Technologies for generating an avatar with a facial expression corresponding to a facial expression of a user include capturing a reference user image of the user on a computing device when the user is expressing a reference facial expression for registration. The computing device generates reference facial measurement data based on the captured reference user image and compares the reference facial measurement data with facial measurement data of a corresponding reference expression of the avatar to generate facial comparison data. After a user has been registered, the computing device captures a real-time facial expression of the user and generates real-time facial measurement data based on the captured real-time image. The computing device applies the facial comparison data to the real-time facial measurement data to generate modified expression data, which is used to generate an avatar with a facial expression corresponding with the facial expression of the user.

    摘要翻译: 用于生成具有与用户的面部表情相对应的面部表情的化身的技术包括当用户表达用于注册的参考面部表情时,在计算设备上捕获用户的参考用户图像。 计算装置基于捕获的参考用户图像生成参考面部测量数据,并将参考面部测量数据与化身的对应参考表达式的面部测量数据进行比较以生成面部比较数据。 在用户注册之后,计算设备捕获用户的实时面部表情,并且基于所捕获的实时图像生成实时面部测量数据。 计算装置将面部比较数据应用于实时面部测量数据,以产生修改后的表达数据,该修改的表情数据用于生成具有与用户面部表情相对应的面部表情的化身。

    IMAGE-BASED MULTI-VIEW 3D FACE GENERATION
    10.
    发明申请
    IMAGE-BASED MULTI-VIEW 3D FACE GENERATION 审中-公开
    基于图像的多视图3D面产生

    公开(公告)号:US20130201187A1

    公开(公告)日:2013-08-08

    申请号:US13522783

    申请日:2011-08-09

    IPC分类号: G06T17/00

    摘要: Systems, devices and methods are described including recovering camera parameters and sparse key points for multiple 2D facial images and applying a multi-view stereo process to generate a dense avatar mesh using the camera parameters and sparse key points. The dense avatar mesh may then be used to generate a 3D face model and multi-view texture synthesis may be applied to generate a texture image for the 3D face model.

    摘要翻译: 描述了系统,设备和方法,包括恢复用于多个2D面部图像的相机参数和稀疏关键点,并应用多视点立体声处理以使用相机参数和稀疏关键点来生成致密头像网格。 然后可以使用致密的头像网格来生成3D面部模型,并且可以应用多视图纹理合成来生成3D脸部模型的纹理图像。