公开(公告)号：US09142055B1

公开(公告)日：2015-09-22

申请号：US13175765

申请日：2011-07-01

申请人： Jason Smith ,  Kiran S. Bhat

发明人： Jason Smith ,  Kiran S. Bhat

IPC分类号： G06T13/40 ,  G06T19/20 ,  A61F9/008

CPC分类号： G06T13/40 ,  A61F9/00804 ,  G06F17/50 ,  G06T19/20

摘要： This disclosure describes technology, which can be implemented as a method, apparatus, and/or computer software embodied in a computer-readable medium, capable of deforming internal geometry within an outer geometry to account for light bending due to refraction, for example, for real-time modeling of a gaze direction of a 3D computer generated character's eyes. In some implementations, internal eye geometry can be deformed to capture the effect of refraction in real-time such that the gaze direction of a 3D character's eyes can be modeled during an animation phase prior to a rendering phase in the production of a computer generated motion picture.

摘要翻译： 本公开描述了技术，其可以被实现为体现在计算机可读介质中的方法，装置和/或计算机软件，其能够使外部几何中的内部几何形状变形以解决由于折射引起的光弯曲，例如， 三维计算机视线方向的实时建模生成角色的眼睛。 在一些实施方案中，内部眼睛几何可以变形以实时获得折射效应，使得3D角色的眼睛的视线方向可以在生成计算机生成运动的渲染阶段之前的动画阶段期间被建模 图片。

公开(公告)号：US09001132B1

公开(公告)日：2015-04-07

申请号：US13324808

申请日：2011-12-13

申请人： Kevin Wooley ,  Kiran S. Bhat ,  Michael Sanders

发明人： Kevin Wooley ,  Kiran S. Bhat ,  Michael Sanders

IPC分类号： G06T13/00 ,  G09G5/00

CPC分类号： G09G5/00 ,  G06K9/00335 ,  G06T7/251 ,  G06T13/40 ,  G06T2207/30196

摘要： A computer-implemented method for providing retargeting of actor motion includes: receiving, in a computer system, an input generated by user selection of at least one of multiple real-time constraint scenarios, each real-time constraint scenario corresponding to a relationship between motion capture information from an actor and a position or movement of a character driven by the motion capture information; activating, based on the selected real-time constraint scenario, one or more of multiple limb solvers for the character which determines at least a first joint angle for a corresponding character limb; registering, for at least one character limb where the corresponding limb solver is not activated, a corresponding joint angle from the motion capture information as a second joint angle; and determining a root location for the character based on at least the first and second joint angles.

摘要翻译： 用于提供演员运动的重定向的计算机实现的方法包括：在计算机系统中接收由用户选择多个实时约束场景中的至少一个生成的输入，每个实时约束场景对应于运动之间的关系 从运动捕获信息捕获来自运动员的信息和由运动捕捉信息驱动的角色的位置或运动; 基于所选择的实时约束场景来激活角色的多个肢体解算器中的一个或多个，其确定相应角色肢体的至少第一关节角度; 对于对应的肢体解算器未被激活的至少一个角色肢体，注册作为第二关节角度的来自运动捕捉信息的对应关节角度; 以及至少基于所述第一和第二关节角确定所述角色的根位置。

公开(公告)号：US08112254B1

公开(公告)日：2012-02-07

申请号：US12113585

申请日：2008-05-01

申请人： Kiran S. Bhat ,  Cary Phillips

发明人： Kiran S. Bhat ,  Cary Phillips

IPC分类号： G06F17/50

CPC分类号： G06T19/20 ,  G06T13/40

摘要： The subject matter of this specification can be embodied in, among other things, a system that includes a correspondence generator that determines a distance-based mapping between a set of points in a source object and a point in a target object and stores the distance-based mapping in a surface map. The system also includes an attribute transfer module that transfers surface attributes that determine an appearance or deformation of the set of points in the source object to the point in the target object using the surface map. The system also includes an attribute editor that receives a selection of a region of the target object and applies an interpolation algorithm that determines new values for surface attributes in the selected region from neighboring points in the target object.

摘要翻译： 本说明书的主题可以包括包括对应生成器的系统，该对应生成器确定源对象中的一组点与目标对象中的点之间的基于距离的映射，并且存储距离 - 基于地图的映射。 该系统还包括一个属性传递模块，其传送表面属性，该表面属性使用表面图将源对象中的点集合的外观或变形确定到目标​​对象中的点。 该系统还包括一个属性编辑器，该属性编辑器接收目标对象的区域的选择，并应用一个内插算法，该对象对象中的相邻点确定所选区域中表面属性的新值。

公开(公告)号：US10269165B1

公开(公告)日：2019-04-23

申请号：US13361350

申请日：2012-01-30

申请人： Kiran S. Bhat ,  Michael Koperwas ,  Rachel M. Rose ,  Jung-Seung Hong ,  Frederic P. Pighin ,  Christopher David Twigg ,  Cary Phillips ,  Steve Sullivan

发明人： Kiran S. Bhat ,  Michael Koperwas ,  Rachel M. Rose ,  Jung-Seung Hong ,  Frederic P. Pighin ,  Christopher David Twigg ,  Cary Phillips ,  Steve Sullivan

IPC分类号： G06T13/40

摘要： A system includes a computing device that includes a memory and a processor configured to execute instructions to perform a method that includes receiving multiple representations of one or more expressions of an object. Each representation includes position information attained from one or more images of the object. The method also includes producing an animation model from one or more groups of controls that respectively define each of the one or more expressions of the object as provided by the multiple representations. Each control of each group of controls has an adjustable value that defines the geometry of at least one shape of a portion of the respective expression of the object. Producing the animation model includes producing one or more corrective shapes if the animation model is incapable of accurately presenting the one or more expressions of the object as provided by the multiple representations.

公开(公告)号：US08854376B1

公开(公告)日：2014-10-07

申请号：US12512454

申请日：2009-07-30

申请人： Kiran S. Bhat ,  Frederic P. Pighin ,  Michael Koperwas ,  Steve Sullivan

发明人： Kiran S. Bhat ,  Frederic P. Pighin ,  Michael Koperwas ,  Steve Sullivan

IPC分类号： G06T13/00

CPC分类号： G06T13/40 ,  G06F3/011 ,  G06T7/251 ,  G06T17/20 ,  G06T19/20 ,  G06T2207/30196 ,  G06T2219/2021

摘要： A motion library can be created by generating motion feature vectors for at least some of multiple frames of a video sequence using a 3D mesh, each motion feature vector corresponding to characteristics of the body deformation in one of the frames. The A user can select a subset of the frames. For each frame in the subset, the user can define settings for controls of an animation character, the settings selected by the user to correspond to the body deformation in the respective frame. Mappings are generated using the settings and the motion feature vectors, the mappings regulating the controls based on multiple motion feature vectors. The motion library can be used to generate an animation from an actor performance.

摘要翻译： 可以通过使用3D网格为视频序列的多个帧的至少一些帧生成运动特征向量来创建运动库，每个运动特征向量对应于帧中的一个中的身体变形的特征。 A用户可以选择一个帧的子集。 对于子集中的每个帧，用户可以定义用于控制动画角色的设置，用户选择的设置对应于相应帧中的身体变形。 使用设置和运动特征向量生成映射，基于多个运动特征向量来调节控件的映射。 运动库可用于从演员表演中生成动画。

公开(公告)号：US08666119B1

公开(公告)日：2014-03-04

申请号：US13306572

申请日：2011-11-29

申请人： Ronald Mallet ,  Kiran S. Bhat ,  Kevin Wooley

发明人： Ronald Mallet ,  Kiran S. Bhat ,  Kevin Wooley

IPC分类号： G06K9/00

CPC分类号： G06K9/00 ,  G06T7/251 ,  G06T19/00 ,  G06T2207/10016 ,  G06T2207/30196

摘要： A first frame includes a first 2D image of a motion capture subject in the real 3D space. A 3D model is deformed into a first deformation and placing the deformed 3D model in a virtual 3D space in a first location so that the deformed 3D model corresponds to the first 2D image. A second frame includes a second 2D image of the motion capture subject in the real 3D space. 2D changes in the second 2D image relative to the first 2D image are tracked. The 2D changes are projected on the virtual 3D space as 3D constraints. Based on the second 2D image, the 3D model is again deformed into a second deformation and placing the 3D model in the virtual 3D space in a second location in conformance with the 3D constraints.

摘要翻译： 第一帧包括实际3D空间中的运动捕捉对象的第一2D图像。 将3D模型变形为第一变形并将变形的3D模型放置在第一位置中的虚拟3D空间中，使得变形的3D模型对应于第一2D图像。 第二帧包括实际3D空间中的运动捕捉对象的第二2D图像。 跟踪第二2D图像中相对于第一2D图像的二维变化。 2D变化作为3D约束被投影在虚拟3D空间上。 基于第二2D图像，3D模型再次变形为第二变形，并且将3D模型放置在符合3D约束的第二位置中的虚拟3D空间中。

公开(公告)号：US09196074B1

公开(公告)日：2015-11-24

申请号：US13168389

申请日：2011-06-24

申请人： Kiran S. Bhat ,  Delio Tramontozzi ,  Tim Harrington

发明人： Kiran S. Bhat ,  Delio Tramontozzi ,  Tim Harrington

IPC分类号： G06T13/40

CPC分类号： G06T13/40 ,  G06T17/20

摘要： A system includes a computing device that includes a memory configured to store instructions. The computing device also includes a processor configured to execute the instructions to perform a method that includes producing an animation model from one or more representations of an object provided from a deformable likeness of the object. The one or more representations are based upon position information from a collection of images of the object captured by at least one camera. The method also includes refining the animation model to produce representations that substantially match the one or more representations provided by the deformable likeness of the object. Refining the animation model is based upon the position information from the collection of images of the object and one or more constraints.

摘要翻译： 系统包括计算设备，其包括被配置为存储指令的存储器。 计算设备还包括处理器，其被配置为执行指令以执行包括从对象的可变形相似性提供的对象的一个​​或多个表示中产生动画模型的方法。 一个或多个表示基于来自由至少一个照相机捕获的对象的图像的集合的位置信息。 该方法还包括改进动画模型以产生基本上匹配由对象的可变形相似性提供的一个或多个表示的表示。 精炼动画模型基于来自对象的图像的集合的位置信息和一个或多个约束。

公开(公告)号：US08649555B1

公开(公告)日：2014-02-11

申请号：US12607480

申请日：2009-10-28

申请人： Christoph Bregler ,  Kiran S. Bhat ,  Brett A. Allen

发明人： Christoph Bregler ,  Kiran S. Bhat ,  Brett A. Allen

IPC分类号： G06K9/00 ,  G06K9/62

CPC分类号： G06K9/00624 ,  G06K9/00248 ,  G06K9/3216 ,  G06K2009/3225 ,  G06K2009/366 ,  G06T7/251 ,  G06T2207/30201 ,  G06T2207/30204

摘要： A computer program product tangibly embodied in a computer-readable storage medium includes instructions that when executed by a processor perform a method. The method includes identifying a frame of a video sequence, transforming a model into an initial guess for how the region appears in the frame, performing an exhaustive search of the frame, performing a plurality of optimization procedures, wherein at least one additional model parameter is taken into account as each subsequent optimization procedure is initiated. A system includes a computer readable storage medium, a graphical user interface, an input device, a model for texture and shape of the region, the model generated using the video sequence and stored in the computer readable storage medium, and a solver component.

摘要翻译： 有形地体现在计算机可读存储介质中的计算机程序产品包括当由处理器执行时执行方法的指令。 该方法包括识别视频序列的帧，将模型变换成如何区域出现在帧中的初始猜测，执行帧的穷尽搜索，执行多个优化过程，其中至少一个附加模型参数是 考虑到每个随后的优化过程被启动。 系统包括计算机可读存储介质，图形用户界面，输入设备，用于区域的纹理和形状的模型，使用视频序列生成并存储在计算机可读存储介质中的模型以及求解器组件。