专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20060013449A1 Facial image processing methods and systems 有权
公开(公告)号：US20060013449A1
公开(公告)日：2006-01-19
申请号：US11217540
申请日：2005-09-01
申请人： Stephen Marschner , Brian Guenter , Sashi Raghupathy , Kirk Olynyk , Sing Kang
发明人： Stephen Marschner , Brian Guenter , Sashi Raghupathy , Kirk Olynyk , Sing Kang
IPC分类号： G06K9/00
CPC分类号： G06K9/4661 , G06K9/00268 , G06T7/521 , G06T15/506
摘要： In the described embodiment, methods and systems for processing facial image data for use in animation are described. In one embodiment, a system is provided that illuminates a face with illumination that is sufficient to enable the simultaneous capture of both structure data, e.g. a range or depth map, and reflectance properties, e.g. the diffuse reflectance of a subject's face. This captured information can then be used for various facial animation operations, among which are included expression recognition and expression transformation.

2. 发明申请

US20050089199A1 Facial image processing methods and systems 有权
公开(公告)号：US20050089199A1
公开(公告)日：2005-04-28
申请号：US10980073
申请日：2004-11-02
申请人： Stephen Marschner , Brian Guenter , Sashi Raghupathy , Kirk Olynyk , Sing Kang
发明人： Stephen Marschner , Brian Guenter , Sashi Raghupathy , Kirk Olynyk , Sing Kang
IPC分类号： G06T1/00 , G06F7/60 , G06F9/455 , G06F17/10 , G06K9/00 , G06K9/46 , G06T7/00 , G06T15/50 , G06T15/60
CPC分类号： G06K9/4661 , G06K9/00268 , G06T7/521 , G06T15/506
摘要： In the described embodiment, methods and systems for processing facial image data for use in animation are described. In one embodiment, a system is provided that illuminates a face with illumination that is sufficient to enable the simultaneous capture of both structure data, e.g. a range or depth map, and reflectance properties, e.g. the diffuse reflectance of a subject's face. This captured information can then be used for various facial animation operations, among which are included expression recognition and expression transformation.

3. 发明申请

US20060192785A1 Methods and systems for animating facial features, and methods and systems for expression transformation 有权
公开(公告)号：US20060192785A1
公开(公告)日：2006-08-31
申请号：US11409813
申请日：2006-04-24
申请人： Stephen Marschner , Brian Guenter , Sashi Raghupathy , Kirk Olynyk , Sing Kang
发明人： Stephen Marschner , Brian Guenter , Sashi Raghupathy , Kirk Olynyk , Sing Kang
IPC分类号： G06T15/70
CPC分类号： G06T13/40 , G06T15/04 , G06T17/10 , G06T17/20 , G06T17/205 , G06T2200/08 , Y10S345/956
摘要： The illustrated and described embodiments describe techniques for capturing data that describes 3-dimensional (3-D) aspects of a face, transforming facial motion from one individual to another in a realistic manner, and modeling skin reflectance.

4. 发明申请

US20060095489A1 Representation of implicit curves for procedural surfaces 有权
标题翻译：表示程序表面的隐式曲线
公开(公告)号：US20060095489A1
公开(公告)日：2006-05-04
申请号：US10977731
申请日：2004-10-28
申请人： Brian Guenter
发明人： Brian Guenter
IPC分类号： G06F17/14
CPC分类号： G06T17/30
摘要： Compact and accurate piecewise parametric representations of implicit functions may be achieved by iteratively selecting ranges of parameterizing regions and testing each for satisfying an intervalized super convergence test. In one aspect, the implicit function is represented as a compact form of one or more representations of such convergence regions. In yet another aspect, iteration is begun with applying the intervalized convergence test to an entire pameterization region. In yet another aspect, the range being tested for super convergence is iteratively sub-divided to generate other ranges for testing. In one aspect, such sub-dividing comprises dividing the selected ranges by half. In one further aspect, Newton iterate steps are applied to selected ranges to change such ranges for further testing of super convergence of such ranges. Parametric representations that use such representations of convergence regions to express implicit functions consume far less memory for storage than conventional representations. Algorithms are described herein for quickly calculating such representations.
摘要翻译：可以通过迭代地选择参数化区域的范围并测试每个范围来满足间隔超收敛测试来实现隐式函数的紧凑和准确的分段参数表示。在一个方面，隐含函数被表示为这种会聚区域的一个或多个表示形式的紧凑形式。在另一方面，通过将间隔收敛测试应用于整个参数化区域来开始迭代。在另一方面，被测试超级收敛的范围被迭代地细分，以产生用于测试的其他范围。在一个方面，这种分割包括将所选择的范围除以一半。在另一方面，将牛顿迭代步骤应用于所选择的范围以改变这样的范围，以进一步测试这种范围的超级收敛。使用收敛区域的这种表示来表达隐含函数的参数表示与常规表示相比消耗的存储空间要少得多。这里描述了用于快速计算这种表示的算法。

5. 发明申请

US20050062743A1 Methods and systems for animating facial features and methods and systems for expression transformation 有权
标题翻译：用于动画面部特征的方法和系统，用于表达变换的方法和系统
公开(公告)号：US20050062743A1
公开(公告)日：2005-03-24
申请号：US10980760
申请日：2004-11-02
申请人： Stephen Marschner , Brian Guenter , Sashi Raghupathy , Kirk Olynyk , Sing Kang
发明人： Stephen Marschner , Brian Guenter , Sashi Raghupathy , Kirk Olynyk , Sing Kang
IPC分类号： G06T1/00 , G06T7/20 , G06T13/40 , G06T15/04 , G06T17/10 , G06T17/20 , G06T15/70
CPC分类号： G06T13/40 , G06T15/04 , G06T17/10 , G06T17/20 , G06T17/205 , G06T2200/08 , Y10S345/956
摘要： The illustrated and described embodiments describe techniques for capturing data that describes 3-dimensional (3-D) aspects of a face, transforming facial motion from one individual to another in a realistic manner, and modeling skin reflectance.
摘要翻译：所示出和描述的实施例描述了用于捕获描述面部的三维（3-D）方面的数据的技术，以现实的方式将面部运动从一个个体转换到另一个个体，以及对皮肤反射率进行建模。

6. 发明申请

US20070002043A1 Triangulating procedural geometric objects 有权
标题翻译：三角形程序几何对象
公开(公告)号：US20070002043A1
公开(公告)日：2007-01-04
申请号：US11172653
申请日：2005-06-30
申请人： Brian Guenter , Marcel Gavriliu
发明人： Brian Guenter , Marcel Gavriliu
IPC分类号： G06T17/00
CPC分类号： G06T17/20 , G06T17/10
摘要： A complex procedural surface can be expressed based on some constructive solid geometry operations performed on primitive procedural surfaces. The domain based representation of the complex procedural surface includes implicit curves of intersection. During pre-processing, the parts of the domain based representation to be triangulated are first sub-divided into simple triangles not bound on any side by an edge related to the parameterized regions of the implicit curve and curve visibility triangles. The coarse pre-processed triangulated mesh is later refined during runtime by further sub-dividing the coarse mesh to add triangles with curve based edges and non-curve based edges to generate a mesh of sampling triangles. The more refined sampling triangle mesh is further refined by applying geometry instancing to map appropriate instance meshes into the appropriate sampling triangles to create an even more refined triangulated mesh at runtime for rendering.
摘要翻译：可以基于在原始程序表面上执行的一些建构性实体几何操作来表达复杂的程序表面。复杂程序表面的基于域的表示包括交集的隐式曲线。在预处理期间，要进行三角测量的基于域的表示的部分首先被细分为简单的三角形，而不是通过与隐式曲线和曲线可见性三角形的参数化区域相关的边缘在任何一边。粗糙的预处理三角网格在运行时间之后通过进一步细分粗糙网格以添加具有基于曲线的边缘和非基于曲线的边缘的三角形，以生成采样三角形的网格，以后进行细化。更精细的采样三角形网格进一步通过应用几何体实例来将适当的实例网格映射到适当的采样三角形中，以在运行时创建更精细的三角网格以进行渲染。

7. 发明申请

US20060101103A1 Representing implicit curves of procedural geometric surfaces 有权
标题翻译：表示程序几何表面的隐式曲线
公开(公告)号：US20060101103A1
公开(公告)日：2006-05-11
申请号：US11213553
申请日：2005-08-26
申请人： Brian Guenter
发明人： Brian Guenter
IPC分类号： G06F1/16
CPC分类号： G06T17/10 , G06T17/30 , G06T2210/21
摘要： Compact and accurate piecewise parametric representations of implicit curves may be achieved by iteratively selecting ranges of parameterizing regions and testing each for satisfying an intervalized super convergence test. In one aspect, the implicit curves is represented as a compact form of one or more representations of such convergence regions. For memory and bandwidth constrained applications, starting points of convergence regions may not be stored but instead calculated at runtime prior to rendering a point on the implicit curve. Furthermore, not all endpoints relevant convergence regions of a selected implicit curve need be stored. Instead, based on at least one endpoint, the other endpoints can be derived via Newton iterations. To further reduce memory and bandwidth costs, coordinates can be stored in a quantized format and the points reflecting floating point accuracy can be derived at runtime again by Newton iteration.
摘要翻译：可以通过迭代地选择参数化区域的范围并测试每个范围来满足间隔超收敛测试来实现隐式曲线的紧凑和准确的分段参数表示。在一个方面，隐式曲线被表示为这种会聚区域的一个或多个表示的紧凑形式。对于内存和带宽受限的应用程序，收敛区域的起始点可能不存储，而是在隐式曲线上渲染点之前在运行时计算。此外，并不需要存储所选隐式曲线的所有端点相关收敛区域。相反，基于至少一个端点，其他端点可以通过牛顿迭代得到。为了进一步降低内存和带宽成本，可以以量化格式存储坐标，并且可以在运行时再次通过牛顿迭代得到反映浮点精度的点。

8. 发明授权

US06072496A Method and system for capturing and representing 3D geometry, color and shading of facial expressions and other animated objects 失效
标题翻译：用于捕获和表示面部表情和其他动画对象的3D几何，颜色和阴影的方法和系统
公开(公告)号：US06072496A
公开(公告)日：2000-06-06
申请号：US93590
申请日：1998-06-08
申请人： Brian Guenter , Cindy Marie Grimm , Henrique Sarmento Malvar
发明人： Brian Guenter , Cindy Marie Grimm , Henrique Sarmento Malvar
IPC分类号： G06K9/00 , G06T1/00 , G06T7/00 , G06T13/40 , G06F15/00
CPC分类号： G06K9/00255 , G06K9/00201 , G06K9/00315 , G06K9/3216 , G06T13/40 , G06T7/0075 , G06T2200/08
摘要： The method captures a 3D model of a face, which includes a 3D mesh and a series of deformations of the mesh that define changes in position of the mesh over time (e.g., for each frame). The method also builds a texture map associated with each frame in an animation sequence. The method achieves significant advantages by using markers on an actor's face to track motion of the face over time and to establish a relationship between the 3D model and texture. Specifically, videos of an actor's face with markers are captured from multiple cameras. Stereo matching is used to derive 3D locations of the markers in each frame. A 3D scan is also performed on the actor's face with the markers to produce an initial mesh with markers. The markers from the 3D scan are matched with the 3D locations of the markers in each frame from the stereo matching process. The method determines how the position of the mesh changes from frame to frame by matching the 3D locations of the markers from one frame to the next. The method derives textures for each frame by removing the dots from the video data, finding a mapping between texture space and the 3D space of the mesh, and combining the camera views for each frame into a signal texture map. The data needed to represent facial animation includes: 1) an initial 3D mesh, 2) 3D deformations of the mesh per frame, and 3) a texture map associated with each deformation. The method compresses 3D geometry by decomposing the deformation data into basis vectors and coefficients. The method compresses the textures using video compression.
摘要翻译：该方法捕获面部的3D模型，其包括3D网格和网格的一系列变形，其定义网格随时间的位置的变化（例如，对于每个帧）。该方法还构建与动画序列中的每个帧相关联的纹理映射。该方法通过使用演员脸部上的标记来随着时间的推移跟踪脸部的运动并建立3D模型和纹理之间的关系，实现了显着的优点。具体来说，从多个摄像机捕获带有标记的演员脸部的视频。立体匹配用于导出每个帧中标记的3D位置。还使用标记对演员的脸部进行3D扫描，以产生具有标记的初始网格。来自3D扫描的标记与来自立体匹配处理的每帧中的标记的3D位置相匹配。该方法通过将标记的3D位置从一帧匹配到下一个帧来确定网格的位置如何从帧到帧的变化。该方法通过从视频数据中删除点，找到纹理空间与网格的3D空间之间的映射，并将每个帧的相机视图组合成信号纹理贴图，从而获得每个帧的纹理。表示面部动画所需的数据包括：1）初始3D网格，2）每帧网格的3D变形，3）与每个变形相关联的纹理图。该方法通过将变形数据分解为基矢量和系数来压缩3D几何。该方法使用视频压缩来压缩纹理。

9. 发明申请

US20070025634A1 Demosaicing graphical content 失效
公开(公告)号：US20070025634A1
公开(公告)日：2007-02-01
申请号：US11541114
申请日：2006-09-29
申请人： Brian Guenter
发明人： Brian Guenter
IPC分类号： G06K9/40
CPC分类号： G06T3/4015
摘要： Demosaicing of graphical content is provided. In an illustrative implementation a demosaicing engine executing one or more demosaicing algorithms is employed to operate on graphical content to provide better quality and higher resolution images. In operation, the demosaicing engine operates in two modes, a training/learning mode, and a run time mode. During training, training-images are analyzed to generate a codebook of mosaic filter table entries, such that each table entry has an associated list of similar training pixel blocks and their associated filters. During run time, a run-time image is broken into pixel blocks. Each pixel block is then compared with the entries of the codebook to find the closest match filter. The list associated with the entry is then processed using a least-squares algorithm to locate the optimal mosaic filter. As a result, higher resolution is achieved without requiring more pixels.

10. 发明申请

US20060015308A1 Facial image processing 有权
标题翻译：面部图像处理
公开(公告)号：US20060015308A1
公开(公告)日：2006-01-19
申请号：US11218164
申请日：2005-09-01
申请人： Stephen Marschner , Brian Guenter , Sashi Raghupathy , Kirk Olynyk , Sing Kang
发明人： Stephen Marschner , Brian Guenter , Sashi Raghupathy , Kirk Olynyk , Sing Kang
IPC分类号： G06F17/10
CPC分类号： G06K9/4661 , G06K9/00268 , G06T7/521 , G06T15/506
摘要： In the described embodiment, methods and systems for processing facial image data for use in animation are described. In one embodiment, a system is provided that illuminates a face with illumination that is sufficient to enable the simultaneous capture of both structure data, e.g. a range or depth map, and reflectance properties, e.g. the diffuse reflectance of a subject's face. This captured information can then be used for various facial animation operations, among which are included expression recognition and expression transformation.
摘要翻译：在所描述的实施例中，描述了用于处理用于动画的面部图像数据的方法和系统。在一个实施例中，提供了一种系统，其利用足以使得能够同时捕获结构数据的照明来照亮面部，例如，范围或深度图，以及反射率特性，例如。受试者面部的漫反射。然后，该捕获的信息可以用于各种面部动画操作，其中包括表达式识别和表达变换。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式