专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

51. 发明申请

US20100067824A1 IMAGE DECOMPOSTION 有权
标题翻译：图像分解
公开(公告)号：US20100067824A1
公开(公告)日：2010-03-18
申请号：US12323663
申请日：2008-11-26
申请人： Kalyan Sunkavalli , Sylvain Paris , Wojciech Matusik
发明人： Kalyan Sunkavalli , Sylvain Paris , Wojciech Matusik
IPC分类号： G06K9/40 , G06K9/36
CPC分类号： G06T7/162 , G06T7/11 , G06T2207/30196
摘要： A computer-implemented method includes segmenting an input image into a plurality of image cues, each image cue representing a unique set of pixels of the input image. For each image cue, the method includes determining a set of image components, wherein each image component is associated with at least one adjustable factor to represent at least one characteristic of the image cue.
摘要翻译：计算机实现的方法包括将输入图像分割成多个图像提示，每个图像提示表示输入图像的唯一的像素集合。对于每个图像提示，该方法包括确定一组图像分量，其中每个图像分量与至少一个可调节因子相关联以表示图像提示的至少一个特征。

52. 发明授权

US07602990B2 Matting using camera arrays 失效
标题翻译：使用相机阵列进行扫描
公开(公告)号：US07602990B2
公开(公告)日：2009-10-13
申请号：US11238741
申请日：2005-09-29
申请人： Wojciech Matusik , Shmuel Avidan
发明人： Wojciech Matusik , Shmuel Avidan
IPC分类号： H04N9/04
CPC分类号： H04N5/272 , H04N5/2226
摘要： A method extracts an alpha matte from images acquired of a scene by cameras. A depth plane is selected for a foreground in the scene. A trimap is determined from a set of images acquired of the scene. An epipolar plane image is constructed from the set of images and the trimap, the epipolar plane image including scan lines. Variances of intensities are measured along the scan lines in the epipolar image, and an alpha matte is extracted according to the variances.
摘要翻译：一种方法是从相机拍摄的场景中提取出一个阿尔法哑光。为场景中的前景选择深度平面。从获取的场景的一组图像确定微分。由该组图像和微分子构成对极平面图像，包括扫描线的对极平面图像。沿着对极图像中的扫描线测量强度的差异，并且根据方差提取α哑光。

53. 发明申请

US20080223131A1 System and Method for Motion Capture in Natural Environments 失效
标题翻译：自然环境中运动捕捉的系统和方法
公开(公告)号：US20080223131A1
公开(公告)日：2008-09-18
申请号：US11686507
申请日：2007-03-15
申请人： Giovanni Vannucci , Wojciech Matusik , Daniel Vlasic
发明人： Giovanni Vannucci , Wojciech Matusik , Daniel Vlasic
IPC分类号： G01C23/00 , G01P15/18 , G01S11/14
CPC分类号： G01S11/14 , A61B5/112 , A61B5/1122 , A61B5/1126 , A61B5/725 , A61B2562/0219 , G01C21/005 , G01C22/006 , G06F19/00
摘要： A system captures motion data in natural environments. A set of sources and a set of sensors are arranged on an object such as a human body. Each source emits ultrasonic signals detected by the sensors. A driver module is also arranged on the body. The driver module generates the ultrasonic signals for the set of sources and timing signals for the set of sensors. Distances between the set of sources and the set of sensors are measured based on a time of flight of the ultrasonic signals. Three dimensional locations of the set of sources and the set of sensors are determined from the distances. The distance measurements are refined using inertial components that provide rotation rates and accelerations. All these measurements together yield poses or configurations of the object.
摘要翻译：系统在自然环境中捕获运动数据。一组源和一组传感器被布置在诸如人体的物体上。每个源发射由传感器检测到的超声波信号。驾驶员模块也布置在车身上。驱动器模块为该组传感器的一组源和定时信号产生超声波信号。根据超声波信号的飞行时间来测量源组和传感器组之间的距离。根据距离确定源组和传感器组的三维位置。使用提供旋转速度和加速度的惯性部件来改进距离测量。所有这些测量一起产生对象的姿势或配置。

54. 发明申请

US20070070200A1 Video matting using camera arrays 失效
标题翻译：使用相机阵列的视频消光
公开(公告)号：US20070070200A1
公开(公告)日：2007-03-29
申请号：US11388499
申请日：2006-03-24
申请人： Wojciech Matusik , Shmuel Avidan
发明人： Wojciech Matusik , Shmuel Avidan
IPC分类号： H04N7/18
CPC分类号： H04N5/272 , H04N5/2226
摘要： A method and system for determining an alpha matte for a video is presented. A set of videos is acquired by an array of cameras. A centrally located camera in the array is designated as a reference camera and acquires a reference video. A foreground depth plane is selected from the set of videos. A trimap is determined from variances of pixel intensities in each image. Variances of the intensities of pixels labeled as background and pixels labeled as foreground are extrapolated to the pixels labeled as unknown in the trimap. Means of the intensities of the pixels labeled as background are extrapolated to the pixels labeled as unknown to determine an alpha matte for the reference video.
摘要翻译：提出了一种用于确定视频的Alpha哑光的方法和系统。一组相机获得一组视频。将阵列中心位置的相机指定为参考相机并获取参考视频。从视频集中选择前景深度平面。由每个图像中的像素强度的方差确定微分。标记为背景的像素的强度和标记为前景的像素的差异被外推到在trimap中标记为未知的像素。标记为背景的像素的强度的方式被外推到标记为未知的像素，以确定参考视频的α无光泽。

55. 发明申请

US20070025727A1 Fast switching camera aperture 失效
标题翻译：快速切换相机光圈
公开(公告)号：US20070025727A1
公开(公告)日：2007-02-01
申请号：US11193752
申请日：2005-07-29
申请人： Wojciech Matusik , William Yerazunis
发明人： Wojciech Matusik , William Yerazunis
IPC分类号： G03B9/02
CPC分类号： G03B9/02 , G02B27/281 , G03B15/06 , H04N5/2254 , H04N5/272
摘要： A camera aperture includes a first polarizer and a second polarizer with a polarization 90° with respect to the first polarizer. The second polarizer has a through hole at a center. A polarizing rotator is disposed between the first polarizer and the second polarizer. A size of the aperture is changed when a voltage is applied selectively to the polarizing rotator.
摘要翻译：相机孔径包括第一偏振器和相对于第一偏振器偏振90°的第二偏振器。第二偏振器在中心具有通孔。偏振旋转体设置在第一偏振器和第二偏振器之间。当选择性地向偏光旋转器施加电压时，孔径的尺寸被改变。

56. 发明授权

US10834379B2 2D-to-3D video frame conversion 有权
公开(公告)号：US10834379B2
公开(公告)日：2020-11-10
申请号：US16578420
申请日：2019-09-23
申请人： Mohamed M. Hefeeda , Kiana Ali Asghar Calagari , Mohamed Abdelaziz A Mohamed Elgharib , Wojciech Matusik , Piotr Didyk , Alexandre Kaspar
发明人： Mohamed M. Hefeeda , Kiana Ali Asghar Calagari , Mohamed Abdelaziz A Mohamed Elgharib , Wojciech Matusik , Piotr Didyk , Alexandre Kaspar
IPC分类号： H04N13/268 , G06F16/738 , G06T7/50 , H04N13/261 , G06T7/55 , G06T7/11 , H04N13/00
摘要： A wide spread adoption of 3D videos and technologies is hindered by the lack of high-quality 3D content. One promising solution to address this problem is to use automated 2D-to-3D conversion. However, current conversion methods, while general, produce low-quality results with artefacts that are not acceptable to many viewers. Creating a database of 3D stereoscopic videos with accurate depth is, however, very difficult. Computer generated content can be used to generate high-quality 3D video reference database for 2D-to-3D conversion. The method transfers depth information from frames in the 3D reference database to the target frame while respecting object boundaries. It computes depth maps from the depth gradients, and outputs a stereoscopic video.

57. 发明授权

US09588489B2 Computational highlight holography 有权
标题翻译：计算高光全息术
公开(公告)号：US09588489B2
公开(公告)日：2017-03-07
申请号：US13167601
申请日：2011-06-23
申请人： Christian Regg , Szymon Marek Rusinkiewicz , Wojciech Matusik , Markus Gross
发明人： Christian Regg , Szymon Marek Rusinkiewicz , Wojciech Matusik , Markus Gross
IPC分类号： G03H1/08
CPC分类号： G03H1/0808 , G03H2210/441 , G03H2210/452
摘要： A technique for fabricating a highlight hologram based on a digital object performs point sampling on the object and represents each sampled point as a geometric patch. A set of geometric patches corresponding to sampled points from the object are fabricated into a substrate. A paraboloid patch may be used for reflective substrates while a hyperboloid may be used for transmissive substrates. To avoid specifying overlapping patches, which are impractical to fabricate, certain of the sample points may be merged. An output set of grooves is saved and may be used to specify fabrication of a highlight hologram on the physical substrate.
摘要翻译：基于数字对象制造高光全息图的技术对物体进行点取样，并将每个采样点表示为几何补片。将对应于来自物体的采样点的一组几何斑块制成基底。抛物面贴片可以用于反射基板，而双曲面可以用于透射基底。为了避免指定重叠的补丁，这些补丁是不切合实际的，可能会合并某些采样点。输出的一组凹槽被保存并且可以用于指定物理基板上的高光全息图的制造。

58. 发明授权

US09113043B1 Multi-perspective stereoscopy from light fields 有权
标题翻译：光场多透视立体镜
公开(公告)号：US09113043B1
公开(公告)日：2015-08-18
申请号：US13317658
申请日：2011-10-24
申请人： Changil Kim , Alexander Hornung , Simon Heinzle , Wojciech Matusik , Markus Gross
发明人： Changil Kim , Alexander Hornung , Simon Heinzle , Wojciech Matusik , Markus Gross
IPC分类号： H04N7/18 , H04N13/02 , G09G5/00
CPC分类号： H04N7/18 , G02B27/0172 , G02B2027/0134 , G02B2027/0138 , G02B2027/0178 , G06T3/0093 , G06T15/06 , G06T15/08 , G06T2200/04 , G06T2207/10004 , G06T2207/10016 , G06T2210/61 , G06T2219/2008 , G09G5/00 , H04N13/128 , H04N13/239 , H04N13/271 , H04N13/275 , H04N13/282 , H04N13/31 , H04N13/32 , H04N13/339 , H04N13/349 , H04N13/395 , H04N2013/0081 , H04N2013/0092
摘要： Methods and systems for generating stereoscopic content with granular control over binocular disparity based on multi-perspective imaging from representations of light fields are provided. The stereoscopic content is computed as piecewise continuous cuts through a representation of a light field, minimizing an energy reflecting prescribed parameters such as depth budget, maximum binocular disparity gradient, desired stereoscopic baseline. The methods and systems may be used for efficient and flexible stereoscopic post-processing, such as reducing excessive binocular disparity while preserving perceived depth or retargeting of already captured scenes to various view settings. Moreover, such methods and systems are highly useful for content creation in the context of multi-view autostereoscopic displays and provide a novel conceptual approach to stereoscopic image processing and post-production.
摘要翻译：提供了基于从光场表示的多视角成像产生具有对双目视差的细粒度控制的立体内容的方法和系统。立体内容被计算为通过光场的表示的分段连续切割，最小化反映规定参数的能量，例如深度预算，最大双眼视差梯度，期望的立体基线。方法和系统可以用于有效和灵活的立体后处理，例如减少过度的双目视差，同时保持感测深度或将已捕获的场景重新定位到各种视图设置。此外，这种方法和系统对于在多视点自动立体显示器的背景下的内容创建非常有用，并且提供了一种用于立体图像处理和后期制作的新颖的概念方法。

59. 发明授权

US08643684B2 Multi-layer plenoptic displays that combine multiple emissive and light modulating planes 有权
标题翻译：组合多个发射和光调制平面的多层全光显示器
公开(公告)号：US08643684B2
公开(公告)日：2014-02-04
申请号：US13184693
申请日：2011-07-18
申请人： Nicola V. Ranieri , Simon Heinzle , Peter C. Barnum , Wojciech Matusik , Markus Gross
发明人： Nicola V. Ranieri , Simon Heinzle , Peter C. Barnum , Wojciech Matusik , Markus Gross
IPC分类号： G09G5/02
CPC分类号： G02B27/2214 , G02B27/2278 , H04N13/31 , H04N13/346 , H04N13/351 , H04N13/363
摘要： A multi-planar plenoptic display assembly is provided that includes multiple spatially-varying light emitting and light modulating planes. The display assembly includes at least one light emitting device and may include, but does not require, a modulating device used in conjunction according to display methods taught herein to display light field data. A display assembly controller may be used to render a light field with depth into a multi-planar plenoptic display assembly by assigning decomposed portions of the light field to the display assembly for display or presentation by differing ones of the emitting elements and by operating a modulating device to provide a parallax barrier. In one embodiment, a dynamic parallax barrier and a number of bi-state screens. Another embodiment uses a beam splitter to co-locate two pairs of autostereoscopic displays each including a projector projecting 3D content, a parallax barrier, and an emissive/projector element.
摘要翻译：提供了包括多个空间变化的发光和光调制平面的多平面全光显示组件。显示组件包括至少一个发光装置，并且可以包括但不需要根据本文教导的显示方法结合使用的调制装置来显示光场数据。可以使用显示组件控制器来将具有深度的光场通过将光场的分解部分分配给显示组件以将深度的光场赋予多平面全光显示组件，以通过不同的发光元件进行显示或呈现，并且通过操作调制设备提供视差屏障。在一个实施例中，动态视差屏障和多个双状态屏幕。另一实施例使用分束器来共同定位两对自动立体显示器，每对显示器包括投影3D内容的投影仪，视差屏障和发射/投影仪元件。

60. 发明申请

US20120019882A1 COMPUTATIONAL HIGHLIGHT HOLOGRAPHY 有权
标题翻译：计算亮点全息图
公开(公告)号：US20120019882A1
公开(公告)日：2012-01-26
申请号：US13167601
申请日：2011-06-23
申请人： Christain REGG , Szymon Marek Rusinkiewicz , Wojciech Matusik , Markus Gross
发明人： Christain REGG , Szymon Marek Rusinkiewicz , Wojciech Matusik , Markus Gross
IPC分类号： G03H1/08
CPC分类号： G03H1/0808 , G03H2210/441 , G03H2210/452
摘要： A technique for fabricating a highlight hologram based on a digital object performs point sampling on the object and represents each sampled point as a geometric patch. A set of geometric patches corresponding to sampled points from the object are fabricated into a substrate. A paraboloid patch may be used for reflective substrates while a hyperboloid may be used for transmissive substrates. To avoid specifying overlapping patches, which are impractical to fabricate, certain of the sample points may be merged. An output set of grooves is saved and may be used to specify fabrication of a highlight hologram on the physical substrate.
摘要翻译：基于数字对象制造高光全息图的技术对物体进行点取样，并将每个采样点表示为几何补片。将对应于来自物体的采样点的一组几何斑块制成基底。抛物面贴片可以用于反射基板，而双曲面可以用于透射基底。为了避免指定重叠的补丁，这些补丁是不切合实际的，可能会合并某些采样点。输出的一组凹槽被保存并且可以用于指定物理基板上的高光全息图的制造。

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