公开(公告)号：US20060221248A1

公开(公告)日：2006-10-05

申请号：US11092376

申请日：2005-03-29

申请人： Morgan McGuire ,  Wojciech Matusik ,  Hanspeter Pfister ,  John Hughes ,  Fredo Durand

发明人： Morgan McGuire ,  Wojciech Matusik ,  Hanspeter Pfister ,  John Hughes ,  Fredo Durand

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：US07408591B2

公开(公告)日：2008-08-05

申请号：US11193742

申请日：2005-07-29

申请人： Wojciech Matusik ,  Morgan McGuire

发明人： Wojciech Matusik ,  Morgan McGuire

IPC分类号： H04N9/74

CPC分类号： H04N5/275 ,  G06T7/11 ,  G06T7/194 ,  G06T2207/10016

摘要： A method extracts an alpha matte from a video acquired of a scene. A set of pinhole or narrow aperture images IP is acquired of the scene with a camera aperture set to a relatively large depth-of-field. The scene includes a background B and a foreground F. A corresponding set of wide aperture images IF is acquired of the scene with the camera aperture set to a relatively small depth-of-field. The respective pinhole and wide aperture images are combined to extract an alpha matte according to α=1+(IF−IP)/(B−BF).

摘要翻译： 一种方法从场景获取的视频中提取一个阿尔法无光泽。 在相机孔径设置为相对较大的景深的场景中获取一组针孔或窄孔径图像I 。 该场景包括背景B和前景F.获取相机孔径设置为相对较小的景深的场景的对应的一组宽光圈图像I 。 相应的针孔和宽孔径图像被组合以根据<？in-line-formula description =“In-line Formulas”end =“lead”？> alpha = 1 +（I＆ <？in-line-formula description =“In-line Formulas”end =“tail”？>

公开(公告)号：US20060221209A1

公开(公告)日：2006-10-05

申请号：US11092375

申请日：2005-03-29

申请人： Morgan McGuire ,  Wojciech Matusik ,  Hanspeter Pfister

发明人： Morgan McGuire ,  Wojciech Matusik ,  Hanspeter Pfister

IPC分类号： H01L27/00 ,  H04N5/262 ,  G06K9/32

CPC分类号： H04N5/2254 ,  H01L27/14625 ,  H04N5/2258 ,  H04N5/2355

摘要： A camera system acquires multiple optical characteristics at multiple resolutions of a scene. The camera system includes multiple optical elements arranged as a tree having a multiple of nodes connected by edges. the nodes represent optical elements sharing a single optical center, and the edges representing light paths between the nodes. The tree has the following structure: a single root node acquiring a plenoptic field originating from a scene; nodes with a single child node represent filters, lenses, apertures, and shutters; nodes with multiple child nodes represent beam splitters and leaf nodes represent imaging sensors. Furthermore, a length of the light paths from the roof node to each leaf nodes can be equal.

摘要翻译： 相机系统以场景的多个分辨率获取多个光学特性。 相机系统包括被布置成具有通过边缘连接的多个节点的树的多个光学元件。 节点表示共享单个光学中心的光学元件，并且边缘表示节点之间的光路径。 树具有以下结构：单个根节点获取源自场景的全视场; 具有单个子节点的节点表示滤波器，透镜，孔径和快门; 具有多个子节点的节点表示分束器，叶节点表示成像传感器。 此外，从屋顶节点到每个叶节点的光路的长度可以相等。

公开(公告)号：US07599555B2

公开(公告)日：2009-10-06

申请号：US11092376

申请日：2005-03-29

申请人： Morgan McGuire ,  Wojciech Matusik ,  Hanspeter Pfister ,  John F. Hughes ,  Fredo Durand

发明人： Morgan McGuire ,  Wojciech Matusik ,  Hanspeter Pfister ,  John F. Hughes ,  Fredo Durand

IPC分类号： G06K9/34

CPC分类号： H04N5/272

摘要： A method compresses a set of correlated signals by first converting each signal to a sequence of integers, which are further organized as a set of bit-planes. An inverse accumulator is applied to each bit-plane to produce a bit-plane of shifted bits, which are permuted according to a predetermined permutation to produce bit-planes of permuted bits. Each bit-plane of permuted bits is partitioned into a set of blocks of bits. Syndrome bits are generated for each block of bits according to a rate-adaptive base code. Subsequently, the syndrome bits are decompressed in a decoder to recover the original correlated signals.

摘要翻译： 一种方法通过首先将每个信号转换成整数序列来压缩一组相关信号，该整数序列进一步被组织为一组位平面。 反向累加器被施加到每个位平面以产生位移位的位平面，它们根据预定的排列被排列以产生置换位的位平面。 置换位的每个位平面被划分成一组位块。 根据速率自适应基本码为每个位块产生综合位。 随后，解码器中的校正子位解压缩以恢复原始的相关信号。

公开(公告)号：US20070024756A1

公开(公告)日：2007-02-01

申请号：US11193742

申请日：2005-07-29

申请人： Wojciech Matusik ,  Morgan McGuire

发明人： Wojciech Matusik ,  Morgan McGuire

IPC分类号： H04N9/74

CPC分类号： H04N5/275 ,  G06T7/11 ,  G06T7/194 ,  G06T2207/10016

摘要： A method extracts an alpha matte from a video acquired of a scene. A set of pinhole or narrow aperture images IP is acquired of the scene with a camera aperture set to a relatively large depth-of-field. The scene includes a background B and a foreground F. A corresponding set of wide aperture images IF is acquired of the scene with the camera aperture set to a relatively small depth-of-field. The respective pinhole and wide aperture images are combined to extract an alpha matte according to α=1+(IF−IP)/(B−BF).

摘要翻译： 一种方法从场景获取的视频中提取一个阿尔法无光泽。 在相机孔径设置为相对较大的景深的场景中获取一组针孔或窄孔径图像I 。 该场景包括背景B和前景F.获取相机孔径设置为相对较小的景深的场景的对应的一组宽光圈图像I 。 相应的针孔和宽孔径图像被组合以根据<？in-line-formula description =“In-line Formulas”end =“lead”？> alpha = 1 +（I＆ /（BB F））。 <？in-line-formula description =“In-line Formulas”end =“tail”？>

公开(公告)号：US10025882B2

公开(公告)日：2018-07-17

申请号：US13585383

申请日：2012-08-14

申请人： Ilya Baran ,  Linjie Luo ,  Wojciech Matusik

发明人： Ilya Baran ,  Linjie Luo ,  Wojciech Matusik

IPC分类号： G06G7/48 ,  G06F17/50 ,  B33Y50/00 ,  B29C64/386

摘要： The disclosure provides a technique for recursively partitioning a 3D model of an object into two or more components such that each component fits within a predefined printing volume. The technique includes determining a set of planar cuts each of which partitions the 3D model into at least two components, evaluating one or more objective functions for each cut in the set of planar cuts, and selecting a cut from the set of planar cuts based on the evaluations of the objective functions. In addition, the technique includes, upon determining that a component resulting from the selected cut does not fit within the predefined printing volume, further partitioning that component.

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

IPC分类号： G06F17/50 ,  G06T19/20 ,  G06K9/00 ,  G06T17/00 ,  A61B5/00 ,  G10L21/10

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：US08952959B2

公开(公告)日：2015-02-10

申请号：US13086303

申请日：2011-04-13

申请人： Marc Alexa ,  Wojciech Matusik

发明人： Marc Alexa ,  Wojciech Matusik

IPC分类号： G06T17/00

CPC分类号： G06T17/00

摘要： A three-dimensional relief can be produced from one or more two-dimensional digital (2D) images. A height field is computed from the one or more 2D images and illumination direction information. The height field comprises a multiplicity of geometric surface elements arrayed in a 2D field corresponding to the pixels of the one or more 2D images. Each geometric surface element corresponds to a pixel of each of the digital images and has at least one height parameter representing a displacement from a surface floor. Once the height field is computed, optimizations or adjustments can optionally be made to the height field. The height field can be used to fabricate relief elements in a material, such that each relief element corresponds in shape, position in the height field, and height above the surface floor, to one of the geometric surface elements in the height field.

摘要翻译： 可以从一个或多个二维数字（2D）图像产生三维浮雕。 从一个或多个2D图像和照明方向信息计算高度场。 高度场包括排列在对应于一个或多个2D图像的像素的2D场中的多个几何表面元素。 每个几何表面元素对应于每个数字图像的像素，并且具有至少一个表示来自表层的位移的高度参数。 一旦计算了高度场，就可以选择对高度域进行优化或调整。 高度场可用于制造材料中的浮雕元件，使得每个浮雕元件在高度场中的形状，位置和表面地板上方的高度对应于高度场中的几何表面元件之一。

公开(公告)号：US08669981B1

公开(公告)日：2014-03-11

申请号：US12968026

申请日：2010-12-14

申请人： Daniel Wolfertshofer ,  Marc Alexa ,  Wojciech Matusik

发明人： Daniel Wolfertshofer ,  Marc Alexa ,  Wojciech Matusik

IPC分类号： G06T15/00

CPC分类号： G06T15/00 ,  B29C64/112 ,  B33Y50/00 ,  B33Y80/00 ,  G06T17/00

摘要： A method for generating a self-occlusion surface for an image. The method includes receiving the image, receiving a selection of a material with which to construct the self-occlusion surface, and receiving calibration data associated with the material. A plurality of pits is determined, based on the image and calibration data, to define within the self-occlusion surface. A preview of the self-occlusion surface is rendered based on the plurality of pits and the material.

摘要翻译： 一种用于产生图像的自遮挡表面的方法。 该方法包括接收图像，接收用于构建自遮挡表面的材料的选择，以及接收与该材料相关联的校准数据。 基于图像和校准数据确定多个凹坑以在自遮挡表面内限定。 基于多个凹坑和材料渲染自遮挡表面的预览。

公开(公告)号：US08600538B2

公开(公告)日：2013-12-03

申请号：US13083739

申请日：2011-04-11

申请人： Michael Holroyd ,  Ilya Baran ,  Jason Davis Lawrence ,  Wojciech Matusik

发明人： Michael Holroyd ,  Ilya Baran ,  Jason Davis Lawrence ,  Wojciech Matusik

IPC分类号： G06F19/00 ,  G06K15/02

CPC分类号： B29C65/002 ,  B29C64/141 ,  B33Y50/00 ,  G06K15/1807 ,  Y10T156/10

摘要： A set of two-dimensional layers is determined based on a digital three-dimensional model. An image corresponding to each of the layers is rendered on each of a corresponding number of sheets of at least partially transparent material. The sheets of material are assembled together to produce a three-dimensional structure corresponding to the digital model.

摘要翻译： 基于数字三维模型确定一组二维层。 对应于每个层的图像在相应数量的至少部分透明材料的片材上呈现。 将这些材料组合在一起以产生对应于数字模型的三维结构。