-
公开(公告)号：US20120185218A1
公开(公告)日：2012-07-19
申请号：US13275481
申请日：2011-10-18
申请人： Bernd Bickel , Peter Kaufmann , Bernhard Thomaszewski , Derek Edward Bradley , Philip John Jackson , Stephen R. Marschner , Wojciech Matusik , Markus Gross , Thabo Dominik Beeler
发明人： Bernd Bickel , Peter Kaufmann , Bernhard Thomaszewski , Derek Edward Bradley , Philip John Jackson , Stephen R. Marschner , Wojciech Matusik , Markus Gross , Thabo Dominik Beeler
IPC分类号： G06F17/50
CPC分类号： G06F19/3437 , A61B5/442 , A63F2300/6607 , G06F17/10 , G06F17/5018 , G06K9/00268 , G06T17/00 , G06T19/20 , G06T2207/30201 , G06T2219/2021 , G10L2021/105 , G16H50/50
摘要： A computer-implemented method is provided for physical face cloning to generate a synthetic skin. Rather than attempt to reproduce the mechanical properties of biological tissue, an output-oriented approach is utilized that models the synthetic skin as an elastic material with isotropic and homogeneous properties (e.g., silicone rubber). The method includes capturing a plurality of expressive poses from a human subject and generating a computational model based on one or more material parameters of a material. In one embodiment, the computational model is a compressible neo-Hookean material model configured to simulate deformation behavior of the synthetic skin. The method further includes optimizing a shape geometry of the synthetic skin based on the computational model and the captured expressive poses. An optimization process is provided that varies the thickness of the synthetic skin based on a minimization of an elastic energy with respect to rest state positions of the synthetic skin.
摘要翻译： 提供了用于物理面部克隆以产生合成皮肤的计算机实现的方法。 不是试图再现生物组织的机械性质，而是采用输出导向方法，其将合成皮肤模拟成具有各向同性和均匀性质的弹性材料（例如硅橡胶）。 该方法包括从人类对象捕获多个表现姿态，并且基于材料的一个或多个材料参数生成计算模型。 在一个实施例中，计算模型是被配置为模拟合成皮肤的变形行为的可压缩的新胡克斯材料模型。 该方法还包括基于计算模型和所捕获的表达姿态来优化合成皮肤的形状几何。 提供一种优化方法，其基于相对于合成皮肤的静止状态位置的弹性能量的最小化来改变合成皮肤的厚度。
-
公开(公告)号：US09082222B2
公开(公告)日：2015-07-14
申请号：US13275481
申请日：2011-10-18
申请人： Bernd Bickel , Peter Kaufmann , Bernhard Thomaszewski , Derek Edward Bradley , Philip John Jackson , Stephen R. Marschner , Wojciech Matusik , Markus Gross , Thabo Dominik Beeler
发明人： Bernd Bickel , Peter Kaufmann , Bernhard Thomaszewski , Derek Edward Bradley , Philip John Jackson , Stephen R. Marschner , Wojciech Matusik , Markus Gross , Thabo Dominik Beeler
CPC分类号： G06F19/3437 , A61B5/442 , A63F2300/6607 , G06F17/10 , G06F17/5018 , G06K9/00268 , G06T17/00 , G06T19/20 , G06T2207/30201 , G06T2219/2021 , G10L2021/105 , G16H50/50
摘要： A computer-implemented method is provided for physical face cloning to generate a synthetic skin. Rather than attempt to reproduce the mechanical properties of biological tissue, an output-oriented approach is utilized that models the synthetic skin as an elastic material with isotropic and homogeneous properties (e.g., silicone rubber). The method includes capturing a plurality of expressive poses from a human subject and generating a computational model based on one or more material parameters of a material. In one embodiment, the computational model is a compressible neo-Hookean material model configured to simulate deformation behavior of the synthetic skin. The method further includes optimizing a shape geometry of the synthetic skin based on the computational model and the captured expressive poses. An optimization process is provided that varies the thickness of the synthetic skin based on a minimization of an elastic energy with respect to rest state positions of the synthetic skin.
摘要翻译： 提供了用于物理面部克隆以产生合成皮肤的计算机实现的方法。 不是试图再现生物组织的机械性质，而是采用输出导向方法，其将合成皮肤模拟成具有各向同性和均匀性质的弹性材料（例如硅橡胶）。 该方法包括从人类对象捕获多个表现姿态，并且基于材料的一个或多个材料参数生成计算模型。 在一个实施例中，计算模型是被配置为模拟合成皮肤的变形行为的可压缩的新胡克斯材料模型。 该方法还包括基于计算模型和所捕获的表达姿态来优化合成皮肤的形状几何。 提供一种优化方法，其基于相对于合成皮肤的静止状态位置的弹性能量的最小化来改变合成皮肤的厚度。
-
公开(公告)号：US08611674B1
公开(公告)日：2013-12-17
申请号：US12689172
申请日：2010-01-18
IPC分类号： G06K9/68
CPC分类号： G06K9/68 , G06K9/4661 , G06T15/50
摘要： A computer-implemented method for invariant-based normal estimation. The method includes calculating a set of measured invariants for a point associated with a surface of an object, where the set of measured invariants is based on pixel information that includes lighting information, calculating one or more sets of estimated invariants for the point associated with the surface of the object, where each set of estimated invariants is based on a known lighting environment for the object and a different normal for the point associated with the surface of the object, and determining a first normal for the point associated with the surface of the object that results in the set of measured invariants corresponding to a first set of estimated invariants.
摘要翻译： 一种用于基于不变量的正态估计的计算机实现方法。 该方法包括计算与对象表面相关联的点的一组测量不变量，其中所测量的不变量集合基于包括照明信息的像素信息，为与该对象相关联的点计算一组或多组估计不变量 对象的表面，其中每组估计的不变量基于用于对象的已知照明环境和与对象的表面相关联的点的不同法线，以及确定与该对象的表面相关联的点的第一法线 对象，其导致对应于第一组估计不变量的测量不变量集合。
-
公开(公告)号：US08633926B2
公开(公告)日：2014-01-21
申请号：US12689170
申请日：2010-01-18
CPC分类号： G06T17/00 , H04N13/239
摘要： Techniques are provided for mesoscopic geometry modulation. A first set of mesoscopic details associated with an object is determined by applying a filter to an image of an object. Mesoscopic details included in the first set of mesoscopic details are detectable in the image of the object and are not detectable when generating a coarse geometry reconstruction of the object. A three-dimensional model for the object is generated by modulating the coarse geometry with the first set of mesoscopic details.
摘要翻译： 提供了介观几何调制技术。 通过对对象的图像应用过滤器来确定与对象相关联的第一组介观细节。 包含在第一组介观细节中的介观细节在对象的图像中是可检测的，并且在生成对象的粗略几何重建时不可检测。 通过使用第一组介观细节调制粗略几何生成对象的三维模型。
-
5.发明授权公开(公告)号：US08670606B2
公开(公告)日：2014-03-11
申请号：US12897518
申请日：2010-10-04
IPC分类号： G06K9/00
CPC分类号： G06T7/593 , G06T17/20 , G06T2200/08 , G06T2207/30201
摘要： A computer-implemented method for generating a three-dimensional model of an object. The method includes generating a coarse geometry mesh of the object; calculating an optimization for the coarse geometry mesh based on photometric consistency and surface consistency associated with the coarse geometry mesh; and refining the coarse geometry mesh with the optimization to generate the three-dimensional model for the object.
摘要翻译： 一种用于生成对象的三维模型的计算机实现的方法。 该方法包括生成对象的粗略几何网格; 基于与粗糙几何网格相关联的光度一致性和表面一致性，计算粗略几何网格的优化; 并通过优化来细化粗略几何网格以生成对象的三维模型。
-
公开(公告)号：US08917317B1
公开(公告)日：2014-12-23
申请号：US12689173
申请日：2010-01-18
申请人： Thabo Dominik Beeler
发明人： Thabo Dominik Beeler
IPC分类号： H04N13/02 , G01B11/25 , G06T7/00 , G01B11/245
CPC分类号： G01B11/2504 , G01B11/245 , G06T7/85 , G06T2207/10012 , G06T2207/30208
摘要： A method for calibrating a plurality of cameras. The method includes: for each camera, detecting a projection of a proxy object included in an image captured by the camera; for each camera, detecting surface features associated with the proxy object included in the image captured by the camera; for each combination of two different cameras, determining a correspondence set that maps the detected surface features associated with the proxy object included in the image captured by one camera to the detected surface features associated with the proxy object included in the image captured by the other camera; and generating correspondences between features based on relationships between the different correspondence sets, wherein the correspondences between features can be processed by a camera calibration toolbox to generate camera calibration parameters for each camera in the plurality of cameras.
摘要翻译： 一种用于校准多个照相机的方法。 该方法包括：对于每个相机，检测由相机拍摄的图像中包括的代理对象的投影; 对于每个相机，检测与由相机拍摄的图像中包括的代理对象相关联的表面特征; 对于两个不同相机的每个组合，确定将检测到的与由一个相机拍摄的图像中包括的代理对象相关联的表面特征映射到与由另一相机捕获的图像中包括的代理对象相关联的检测到的表面特征的对应关系 ; 以及基于不同对应集之间的关系产生特征之间的对应关系，其中特征之间的对应可由相机校准工具箱处理，以生成多个相机中的每个相机的相机校准参数。
-
公开(公告)号：US09196089B2
公开(公告)日：2015-11-24
申请号：US13474625
申请日：2012-05-17
申请人： Jose Rafael Tena , Moshe Mahler , Iain Matthews , Hengchin Yeh , Thabo Dominik Beeler , Robert Sumner , Cydni Tetro , John-Thomas C. Ngo
发明人： Jose Rafael Tena , Moshe Mahler , Iain Matthews , Hengchin Yeh , Thabo Dominik Beeler , Robert Sumner , Cydni Tetro , John-Thomas C. Ngo
摘要： Techniques are disclosed for creating digital assets that can be used to personalize themed products. For example, a workflow and pipeline used to generate a 3D model from digital images of a person's face and to manufacture a personalized, physical figurine customized with the 3D model are disclosed. The 3D model of the person's face may be simplified to match a topology of a desired figurine. While the topology is deformed to match that of the figurine, the 3D model retains the geometry of the child's face. Simplifying the topology of the 3D model in this manner allows the mesh to be integrated with or attached to a mesh representing desired figurine.
摘要翻译： 披露了用于创建可用于个性化主题产品的数字资产的技术。 例如，公开了用于从人脸数字图像生成3D模型并且制造用3D模型定制的个性化物理雕像的工作流程和流水线。 可以简化人脸的3D模型以匹配所需雕像的拓扑。 当拓扑变形以匹配小雕像时，3D模型保留了孩子脸部的几何形状。 以这种方式简化3D模型的拓扑结构允许网格与表示所需雕像的网格集成或附加到网格上。
-
-
-
-
-
-
搜索结果
7 条记录 (耗时 0.034 秒)
