-
公开(公告)号：US07609859B2
公开(公告)日：2009-10-27
申请号：US11152528
申请日：2005-06-14
CPC分类号： G06K9/4661
摘要： A method generates a three-dimensional, bi-linear, illumination model for arbitrary faces. A large number of images are acquired of many different faces. For each face, multiple images are acquired with varying poses and varying illumination. A three-mode singular value decomposition is applied to the images to determine parameters of the model. The model can be fit to a probe image of an unknown face. Then, the model can be compared with models of a gallery of images of unknown faces to recognize the face in the probe image.
摘要翻译： 一种方法为任意面生成三维，双线性照明模型。 许多不同的脸部获得了大量的图像。 对于每个脸部，以不同的姿势和变化的照明采集多个图像。 对图像应用三模式奇异值分解以确定模型的参数。 该模型可以适应未知脸部的探针图像。 然后，该模型可以与未知脸部图像库的模型进行比较，以识别探针图像中的脸部。
-
公开(公告)号：US20070229498A1
公开(公告)日：2007-10-04
申请号：US11392917
申请日：2006-03-29
IPC分类号： G06T17/00
CPC分类号： G06T17/20
摘要： The invention provides a system and method for modeling small three-dimensional facial features, such as wrinkles and pores. A scan of a face is acquired. A polygon mesh is constructed from the scan. The polygon mesh is reparameterized to determine a base mesh and a displacement image. The displacement image is partitioned into a plurality of tiles. Statistics for each tile are measured. The statistics is modified to deform the displacement image and the deformed displacement image is combined with the base mesh to synthesize a novel face.
摘要翻译： 本发明提供了一种用于建模诸如皱纹和毛孔的小三维面部特征的系统和方法。 获取脸部扫描。 从扫描构建多边形网格。 重新参数化多边形网格以确定基础网格和位移图像。 位移图像被分割成多个瓦片。 测量每个瓦片的统计数据。 修改统计量以使位移图像变形，并且将变形的位移图像与基准网格组合以合成新颖的面部。
-
公开(公告)号：US20060221248A1
公开(公告)日：2006-10-05
申请号：US11092376
申请日：2005-03-29
IPC分类号： H04N9/74
CPC分类号： H04N5/272
摘要： A method and system extracts a matte from images acquired of a scene. A foreground image focused at a foreground in a scene, a background image focused at a background in the scene, and a pinhole image focused on the entire scene are acquired. These three images can be acquired sequentially by a single camera, or simultaneous by three cameras. In the later case, foreground, background and pinhole sequences of images can be acquired. The pinhole image is compared to the foreground image and the background image to extract a matte representing the scene. The comparison classifies pixels in the images as foreground, background, or unknown pixels. An optimizer minimizes an error function in the form of Fourier image equations using a gradient descent method. The error function expresses pixel intensity differences.
摘要翻译： 方法和系统从场景获取的图像中提取哑光。 获取聚焦在场景中的前景的前景图像，聚焦在场景背景中的背景图像以及聚焦在整个场景上的针孔图像。 这三个图像可以由单个相机顺序获取，或者由三个相机同时获取。 在后一种情况下，可以获取图像的前景，背景和针孔序列。 将针孔图像与前景图像和背景图像进行比较，以提取表示场景的哑光。 比较将图像中的像素分类为前景，背景或未知像素。 优化器使用梯度下降法将傅里叶图像方程式的误差函数最小化。 误差函数表示像素强度差异。
-
公开(公告)号：US20060077204A1
公开(公告)日：2006-04-13
申请号：US10961810
申请日：2004-10-08
申请人： Hanspeter Pfister , Matthias Zwicker , Wei Chen , Liu Ren
发明人： Hanspeter Pfister , Matthias Zwicker , Wei Chen , Liu Ren
IPC分类号： G06T17/00
CPC分类号： G06T15/08
摘要： A method renders a volume data set including a plurality of voxels. A sampling rate for each voxel in a volume data set is determined. Each voxel is filtered according to the sampling rate and pixels for an output image are generated from the filtered voxels.
摘要翻译： 一种方法呈现包括多个体素的体数据集。 确定体数据集中的每个体素的采样率。 根据采样率对每个体素进行滤波，并从滤波体素生成输出图像的像素。
-
公开(公告)号：US20050031194A1
公开(公告)日：2005-02-10
申请号：US10636355
申请日：2003-08-07
CPC分类号： G06K9/00288 , G06T17/00
摘要： A method reconstructs or synthesizes heads from 3D models of heads and 2D silhouettes of heads. A 3D statistical model is generated from multiple real human heads. The 3D statistical model includes a model parameter in the form of basis vectors and corresponding coefficients. Multiple 2D silhouettes of a particular head are acquired using a camera for example. The 3D statistical model is fitted to multiple 2D silhouettes to determine a particular value of the model parameter corresponding to the plurality of 2D silhouettes. Then, the 3D statistical model is rendered according to the particular value of the model parameter to reconstruct the particular head.
摘要翻译： 一种方法从头部的3D模型和头部的2D轮廓重建或合成头部。 一个3D统计模型是从多个真人脑中产生的。 3D统计模型包括基矢量和对应系数形式的模型参数。 使用相机例如获取特定头部的多个2D轮廓。 将3D统计模型拟合到多个2D轮廓以确定对应于多个2D轮廓的模型参数的特定值。 然后，根据模型参数的特定值来渲染3D统计模型以重建特定的头部。
-
公开(公告)号：US06480190B1
公开(公告)日：2002-11-12
申请号：US09240641
申请日：1999-01-29
IPC分类号： G06T1500
CPC分类号： G06T17/20
摘要： Provided is a method representing an object by partitioning a surface of the object into a plurality of cells having a grid resolution related to an image plane resolution. Each cell including a single point and points in adjacent cells are connected by links. Abject attributes are assigned to each point and link, and link attributes are assigned to each link.
摘要翻译： 提供了通过将对象的表面划分成具有与图像平面分辨率相关的网格分辨率的多个单元格来表示对象的方法。 包括单个点的单元格和相邻单元格中的点通过链接连接。 拒绝属性分配给每个点和链接，链接属性被分配给每个链接。
-
17.发明授权Method and apparatus for mapping reflectance while illuminating volume data in a rendering pipeline 有权在渲染管线中照射体数据时映射反射率的方法和装置公开(公告)号：US06426749B1
公开(公告)日：2002-07-30
申请号：US09315264
申请日：1999-05-20
IPC分类号： G06T1700
CPC分类号： G06T15/506 , G06T15/005 , G06T15/08
摘要： Reflection intensities of volume samples of a volume are mapped in a rendering pipeline by determining a reflection vector from a gradient vector associated with a sample and an eye vector associated with the volume. A diffuse reflectance map is indexed by the gradient vector to obtain a diffuse intensity. A specular reflection map is indexed by the gradient vector to obtain a specular intensity in response to a bypass signal being true, and a specular reflection map is indexed by the reflection vector to obtain the specular intensity in response to the bypass signal being false.
摘要翻译： 通过从与样本相关联的梯度向量和与该体积相关联的眼矢量确定反射矢量，将体积体积样本的反射强度映射在渲染管线中。 漫反射图由梯度矢量索引，以获得漫反射强度。 镜面反射图由梯度矢量索引，以响应于旁路信号为真，获得镜面强度，并且反射映射由反射矢量索引，以响应旁路信号为假来获得镜面强度。
-
18.发明授权Method and apparatus for modulating lighting with gradient magnitudes of volume data in a rendering pipeline 有权用于在渲染管线中用体积数据的梯度幅度调制照明的方法和装置公开(公告)号：US06356265B1
公开(公告)日：2002-03-12
申请号：US09316122
申请日：1999-05-20
IPC分类号： G06T1700
CPC分类号： G06T15/506 , G06T15/005 , G06T15/08 , G06T15/50
摘要： An apparatus generates lighting modulation factors for samples in a volume rendering pipeline. The apparatus includes a first arithmetic logic unit squaring a gradient magnitude vector of a sample to produce a squared gradient magnitude. A second arithmetic logic unit produces a gradient magnitude from the squared gradient magnitude. A shift register, connected to the first arithmetic logic unit, truncates a predetermined number of high bits of the squared gradient magnitude. A gradient magnitude modulation register stores modulation parameters. A first multiplexer, connected to the second arithmetic logic unit and the shift register, selects the truncated squared gradient magnitude as an index if an index source signal is true, and the gradient magnitude if the index source signal is false, and a memory table is indexes by the index to produce modulated opacity, emissive, diffuse and specular modulation factors.
摘要翻译： 设备为体绘制流水线中的样品生成照明调制因子。 该装置包括第一算术逻辑单元，对样本的梯度幅度矢量进行平方以产生平方梯度幅度。 第二算术逻辑单元从平方梯度幅度产生梯度幅度。 连接到第一算术逻辑单元的移位寄存器截断预定数量的平方梯度幅度的高位。 梯度幅度调制寄存器存储调制参数。 如果索引源信号为真，连接到第二算术逻辑单元和移位寄存器的第一多路复用器选择截断的平方梯度幅度作为索引，如果索引源信号为假，则选择梯度幅值，存储表是 指数由指数产生调制不透明度，发射，漫反射和镜面调制因子。
-
公开(公告)号：US20080260238A1
公开(公告)日：2008-10-23
申请号：US11738642
申请日：2007-04-23
IPC分类号： G06K9/00
CPC分类号： G06K9/00208 , G06T7/74 , G06T2207/10028
摘要： A method and system determines a pose of an object by comparing an input range image acquired of a scene including the input object to each of a set of reference range image of a reference object, such that each reference range images has an associated different pose, and the reference object is similar to the input object. Then, the pose associated with the reference range image which best matches the input range image is selected as the pose of the input object.
摘要翻译： 方法和系统通过将获取的包括输入对象的场景的输入范围图像与参考对象的一组参考范围图像的每一个进行比较来确定对象的姿态，使得每个参考范围图像具有相关联的不同姿势， 并且引用对象类似于输入对象。 然后，选择与输入范围图像最佳匹配的参考范围图像相关联的姿势作为输入对象的姿态。
-
公开(公告)号：US20080218516A1
公开(公告)日：2008-09-11
申请号：US11683833
申请日：2007-03-08
IPC分类号： G06T15/60
摘要： A method factorizing a sequence of images acquired of a scene into lighting components. The scene is illuminated by a moving light source. An appearance profile is constructed for each pixel in the sequence of images. The appearance profile is a vector representing intensities of the pixel at instances in time. The appearance profiles are factorized into a shadow component, a skylight component, and a sunlight component.
摘要翻译： 将场景获取的图像序列分解为照明组件的方法。 场景由移动的光源照亮。 为图像序列中的每个像素构造外观轮廓。 外观轮廓是表示时间上的像素的强度的矢量。 外观轮廓被分解为阴影部件，天窗部件和阳光部件。
-
-
-
-
-
-
-
-
-
搜索结果
74 条记录 (耗时 0.036 秒)
