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

WO2013162747A1 SYSTEMS, METHODS, AND MEDIA FOR PROVIDING INTERACTIVE REFOCUSING IN IMAGES 审中-公开
标题翻译：用于在图像中提供互动重画的系统，方法和媒体
公开(公告)号：WO2013162747A1
公开(公告)日：2013-10-31
申请号：PCT/US2013/031773
申请日：2013-03-14
申请人： THE TRUSTEES OF COLUMBIA UNIVERSITY IN THE CITY OF NEW YORK
发明人： NAYAR, Shree, K. , MIAU, Daniel , ZHOU, Changyin
IPC分类号： G06K9/40
CPC分类号： H04N5/23212 , G02B27/0075 , G02B27/646 , G06T5/50 , G06T2200/21 , G06T2207/10016 , G06T2207/10024 , G06T2207/10148 , G06T2207/20016 , H04N5/23216 , H04N5/23229 , H04N5/2356
摘要： Systems, methods, and media for providing interactive refocusing are provided, the systems comprising: a lens; an image sensor; and a processor that: causes the image sensor to capture a plurality of images over a predetermined, period of time, wherein each of the plurality of images represents a scene at a different point in time; changes a depth of field between at least a pair of the plurality of images; concatenates the plurality of images to create a duration focal volume in the order in which the images were captured; computes a space-time in-focus image that represents in-focus portions from each of the plurality of images based on the duration focal volume; and computes a space-time index map that identifies an in-focus image for each location of the scene from among the plurality of images based on die duration focal volume and the space-time in-focus image.
摘要翻译：提供了用于提供交互式重新聚焦的系统，方法和介质，所述系统包括：透镜; 图像传感器; 以及处理器，其使得所述图像传感器在预定的时间段内捕获多个图像，其中所述多个图像中的每个图像表示在不同时间点的场景; 改变至少一对所述多个图像之间的景深; 将多个图像连接以按照拍摄图像的顺序创建持续时间焦点容积; 基于所述持续时间焦距体积计算表示来自所述多个图像中的每一个的聚焦部分的时空对焦图像; 并且基于管芯持续时间焦点体积和时空对焦图像，计算从多个图像中识别场景的每个位置的对焦图像的空间 - 时间索引图。

2. 发明申请

WO2009094661A1 METHODS, SYSTEMS, AND MEDIA FOR SWAPPING FACES IN IMAGES 审中-公开
标题翻译：方法，系统和图像中的交换场景的媒体
公开(公告)号：WO2009094661A1
公开(公告)日：2009-07-30
申请号：PCT/US2009/032053
申请日：2009-01-26
申请人： THE TRUSTEES OF COLUMBIA UNIVERSITY IN THE CITY OF NEW YORK , NAYAR, Shree, K. , BELHUMEUR, Peter, N. , BITOUK, Dmitri , KUMAR, Neeraj , DHILLON, Samreen
发明人： NAYAR, Shree, K. , BELHUMEUR, Peter, N. , BITOUK, Dmitri , KUMAR, Neeraj , DHILLON, Samreen
IPC分类号： G09G5/00
CPC分类号： G06T11/60
摘要： Methods, systems, and media for swapping faces in images are provided. In some embodiments, a detected face and face data corresponding to an input image is received. A pose bin associated with the detected face is then identified based on the face data. Next, the detected face is aligned to a generic face associated with the pose bin. At least a portion of a candidate face associated with the pose bin is selected. The at least a portion of the candidate face is then copied to a copy of the input image that is aligned w ith the generic image to form a swapped-face image. The swapped-face image is next aligned to the input image to form an output image, and then the output image is outputted to a display.
摘要翻译：提供了用于在图像中交换面部的方法，系统和介质。在一些实施例中，接收与输入图像相对应的检测到的面部和脸部数据。然后，基于面部数据识别与检测到的面部相关联的姿势仓。接下来，检测到的面对准与姿态仓相关联的通用面。选择与姿势仓相关联的候选面部的至少一部分。候选面部的至少一部分然后被复制到与通用图像对准的输入图像的副本以形成交换面图像。交换面图像接下来与输入图像对齐以形成输出图像，然后将输出图像输出到显示器。

3. 发明申请

WO2005114554A2 CATADIOPTRIC SINGLE CAMERA SYSTEMS HAVING RADIAL EPIPOLAR GEOMETRY AND METHODS AND MEANS THEREOF 审中-公开
标题翻译：具有径向二极体几何特征的单一摄像机系统及其方法及其手段
公开(公告)号：WO2005114554A2
公开(公告)日：2005-12-01
申请号：PCT/US2005/018138
申请日：2005-05-23
申请人： THE TRUSTEES OF COLUMBIA UNIVERSITY IN THE CITY OF NEW YORK , KUTHIRUMMAL, Sujit , NAYAR, Shree, K.
发明人： KUTHIRUMMAL, Sujit , NAYAR, Shree, K.
IPC分类号： G06K9/00
CPC分类号： G02B17/00 , G02B17/08 , G06K9/20 , G06K9/209 , G06T7/557 , G06T7/97 , H04N13/207 , H04N13/218 , H04N13/282
摘要： Catadioptric single camera systems capable of sampling the lightfield of a scene from a locus of circular viewpoints and the methods thereof are described. The epipolar lines of the system are radial, and the systems have foveated vision characteristics. A first embodiment of the invention is directed to a camera A0@0bl5 of looking at a scene through a cylinder with a mirrored inside surface. A second embodiment uses a truncated cone with a mirrored inside surface. A third embodiment uses a first truncated cone with a mirrored outside surface and a second truncated cone with a mirrored inside surface. A fourth embodiment of the invention uses a planar mirror with a truncated cone with a mirrored inside surface. The present invention allows high quality depth information to be gathered by capturing stereo images having radial epipolar lines in a simple and efficient method.
摘要翻译：描述了能够从圆形视点的轨迹对场景的光场采样的反射折射单相机系统及其方法。系统的对极线是径向的，并且系统具有移动视觉特性。本发明的第一实施例涉及一种通过具有镜面内表面的圆柱体观察场景的照相机A0 @ 0bl5。第二实施例使用具有镜面内表面的截头圆锥体。第三实施例使用具有镜面外表面的第一截锥体和具有镜面内表面的第二截锥体。本发明的第四实施例使用具有带有镜面内表面的截头锥体的平面镜。本发明允许通过以简单且有效的方法捕获具有径向核线的立体图像来收集高质量的深度信息。

4. 发明申请

WO2002085000A1 METHOD AND APPARATUS FOR RECORDING A SEQUENCE OF IMAGES USING A MOVING OPTICAL ELEMENT 审中-公开
标题翻译：用于记录使用移动光学元件的图像序列的方法和装置
公开(公告)号：WO2002085000A1
公开(公告)日：2002-10-24
申请号：PCT/US2002/011908
申请日：2002-04-15
申请人： THE TRUSTEES OF COLUMBIA UNIVERSITY IN THE CITY OF NEW YORK , NAYAR, Shree, K. , SCHECHNER, Yoav, Y.
发明人： NAYAR, Shree, K. , SCHECHNER, Yoav, Y.
IPC分类号： H04N5/225
CPC分类号： G02B5/205 , G01J3/2823 , G01J2003/1217 , G01J2003/1243 , H04N5/217 , H04N5/2254 , H04N5/2353 , H04N5/2355 , H04N5/238 , H04N9/045
摘要： An imager (200) including a spatially varying optical element (204) which moves while the imager records a sequence of images. The optical element (204) can be an intensity reduction filter, a spectral or polarization filter, or a refractive or reflective element. Because the optical element (204) moves between frames, each scene portion is captured under a range of imaging conditions. A spatially varying intensity reduction filter enables imaging of each scene portion using multiple, different exposure to generate a high dynamic range image. A spatially varying spectral or polarization filter enables measurement of the spectral or polarization characteristics of radiation from each scene portion. A refractive or reflective element enables imaging of scene portions under various focal characteristics, thereby providing depth information and producing an image which is focused everywhere. A refractive or reflective element is used to apply different vertical and/or horizontal shifts to the different frames, thereby generating an enhanced-resolution image.
摘要翻译：包括在成像器记录图像序列的同时移动的空间变化的光学元件（204）的成像器（200）。光学元件（204）可以是强度降低滤光器，光谱或偏振滤光器，或折射或反射元件。由于光学元件（204）在帧之间移动，因此在成像条件的范围内捕获每个场景部分。空间变化的强度降低滤波器使得能够使用多个不同的曝光成像每个场景部分以产生高动态范围图像。空间变化的光谱或偏振滤光器能够测量来自每个场景部分的辐射的光谱或偏振特性。折射或反射元件能够在各种焦点特征下对场景部分进行成像，从而提供深度信息并产生在各处聚焦的图像。使用折射或反射元件对不同的帧应用不同的垂直和/或水平移位，由此产生增强分辨率的图像。

5. 发明申请

WO2008141125A1 METHODS AND SYSTEMS FOR CREATING SPEECH-ENABLED AVATARS 审中-公开
标题翻译：用于创建语音启发的方法和系统
公开(公告)号：WO2008141125A1
公开(公告)日：2008-11-20
申请号：PCT/US2008/063159
申请日：2008-05-09
申请人： THE TRUSTEES OF COLUMBIA UNIVERSITY IN THE CITY OF NEW YORK , NAYAR, Shree, K. , BITOUK, Dmitri
发明人： NAYAR, Shree, K. , BITOUK, Dmitri
IPC分类号： G06F3/048
CPC分类号： G06T13/40 , A63F2300/6607 , G10L2021/105
摘要： Methods and systems for creating speech-enabled as atars are pros ided Ju accordance with some embodiments, methods for creating speech-enabled avatars are provided, the method comprising; receiving a single image that includes a face with a distmct facial geometry; comparing points on the distinct facial geometry with corresponding points on a prototype facial surface, w herein the prototype facial surface is modeled by a Hidden Markov Model that has facia! motion parameters; deforming the prototype facial surface based at ieast in part on the comparison; in response to receiving a text input or an audio input, calculating the facia) motion parameters based on a phone set corresponding to the received input; generating a plural ity of facial animations based on the calculated facial motion parameters and the Hidden Markov Model; and generating an avatai from the single image that includes the deformed facial sin face, the plurality of facia! animations, and the audio inpm or an audio wa\ eform corresponding to the text input.
摘要翻译：根据一些实施例，提供了用于创建支持语音的方法和系统，提供了用于创建支持语音的化身的方法，所述方法包括：接收单个图像，其中包含具有绝对面部几何的脸部; 将不同面部几何的点与原型面部表面上的对应点进行比较，这里的原型面部表面由隐藏的马尔科夫模型建模，具有面部！运动参数; 部分基于比较的原型面部表面变形; 响应于接收文本输入或音频输入，基于与所接收的输入相对应的电话机计算面）运动参数; 基于计算的面部运动参数和隐马尔可夫模型生成多个面部动画; 并且从包括变形的面部脸部脸部的单个图像生成avatai，多个面部！动画和音频inpm或与文本输入相对应的音频文件。

6. 发明申请

WO2004001667A2 SYSTEMS AND METHODS FOR DE-BLURRING MOTION BLURRED IMAGES 审中-公开
标题翻译：用于消除运动图像的系统和方法
公开(公告)号：WO2004001667A2
公开(公告)日：2003-12-31
申请号：PCT/US2003/019446
申请日：2003-06-18
申请人： THE TRUSTEES OF COLUMBIA UNIVERSITY IN THE CITY OF NEW YORK , BEN-EZRA, Moshe , NAYAR, Shree, K.
发明人： BEN-EZRA, Moshe , NAYAR, Shree, K.
IPC分类号： G06T
CPC分类号： H04N5/23264 , G06T5/003 , G06T5/50 , G06T7/20 , G06T2207/20201 , H04N5/23248 , H04N5/23254 , H04N5/23258 , H04N5/23277 , H04N5/2628
摘要： Systems and methods for providing a substantially de-blurred image of a scene from a motion blurred image of the scene are disclosed. An exemplary system includes a primary detector for sensing the motion blurred image and generating primary image information representing the blurred image, a secondary detector for sensing two or more secondary images of the scene and for generating secondary image information representing the two or more secondary images, and a processor for determining motion information from the secondary image information, estimating a point spread function for the motion blurred image from the motion information, and applying the estimated point spread function to the primary image information to generate information representing the substantially de-blurred image.
摘要翻译：公开了用于从场景的运动模糊图像提供场景的基本上去模糊的图像的系统和方法。示例性系统包括用于感测运动模糊图像并产生表示模糊图像的主要图像信息的主检测器，用于感测场景的两个或更多个二次图像并用于生成表示两个或更多个次要图像的次要图像信息的次级检测器，以及处理器，用于根据次要图像信息确定运动信息，从运动信息估计运动模糊图像的点扩展函数，以及将估计的点扩展函数应用于主图像信息以产生表示基本上去模糊图像的信息。

7. 发明申请

WO1997043854A1 OMNIDIRECTIONAL IMAGING APPARATUS 审中-公开
标题翻译： OMNIDIRECTIONAL成像装置
公开(公告)号：WO1997043854A1
公开(公告)日：1997-11-20
申请号：PCT/US1997007331
申请日：1997-04-30
申请人： THE TRUSTEES OF COLUMBIA UNIVERSITY IN THE CITY OF NEW YORK
发明人： THE TRUSTEES OF COLUMBIA UNIVERSITY IN THE CITY OF NEW YORK , NAYAR, Shree, K.
IPC分类号： H04N07/00
CPC分类号： G06T3/0062 , G02B13/06 , G08B13/19626 , G08B13/19628 , G08B13/19641 , H04N5/2254 , H04N5/2259 , H04N5/2628 , H04N5/74
摘要： An omnidirectional image apparatus (130) for sensing an image of a substantially hemispherical scene from a single viewpoint, including a truncated, convex, substantially paraboloid-shaped reflector (135) positioned to orthographically reflect an image of the substantially hemispherical scene, and an image sensor (110) positioned to receive the orthographically reflected image. An omnidirectional image projection apparatus for projecting an image of a substantially hemispherical scene as viewed from a single viewpoint, including a means for projecting a collimated beam of light modulated with the image, and a truncated convex substantially paraboloid-shaped reflector positioned to orthographically reflect the collimated beam of light modulated with the image to project the hemispherical scene.
摘要翻译：一种用于从单个视点感测基本上半球形场景的图像的全向图像设备（130），包括定位成正交地反射基本上半球形场景的图像的截顶凸起的大致抛物面形状的反射器（135），以及图像传感器（110）定位成接收正射反射图像。一种全方位图像投影装置，用于投影从单个视点观察的基本上半球形场景的图像，包括用于投影用图像调制的准直光束的装置，以及定位成正交反射的截顶的凸起大致抛物面形反射器准直光束用图像调制以投影半球场景。

8. 发明申请

WO2012061571A1 CAMERA SYSTEMS AND METHODS FOR GIGAPIXEL COMPUTATIONAL IMAGING 审中-公开
标题翻译：摄像机系统和GIGAPIXEL计算成像方法
公开(公告)号：WO2012061571A1
公开(公告)日：2012-05-10
申请号：PCT/US2011/059100
申请日：2011-11-03
申请人： THE TRUSTEES OF COLUMBIA UNIVERSITY IN THE CITY OF NEW YORK , COSSAIRT, Oliver, S. , MIAU, Daniel , NAYAR, Shree, K.
发明人： COSSAIRT, Oliver, S. , MIAU, Daniel , NAYAR, Shree, K.
IPC分类号： H04N5/238
CPC分类号： H04N5/23238 , G02B3/00 , G02B7/027 , G02B13/06 , G02B27/0025 , G03B37/04 , H04N5/2254
摘要： Camera systems and methods for gigapixel computational imaging are provided. In some embodiments, the camera system comprises: a ball lens, an array of image sensors disposed at a distance from the ball lens, the array of image sensors configured to acquire images from light that passes through the ball lens; and a processor configured to deblur and stitch the images captured by the array of image sensors to generate a gigapixel image.
摘要翻译：提供了用于十亿像素计算成像的相机系统和方法。在一些实施例中，相机系统包括：球形透镜，设置在离球面透镜一定距离处的图像传感器阵列，所述图像传感器阵列被配置为从通过球透镜的光获取图像; 以及处理器，被配置为对图像传感器阵列捕获的图像进行去毛刺和缝合，以生成千兆像素图像。

9. 发明申请

WO2011053678A1 METHODS AND SYSTEMS FOR CODED ROLLING SHUTTER 审中-公开
标题翻译：编码滚筒快门的方法和系统
公开(公告)号：WO2011053678A1
公开(公告)日：2011-05-05
申请号：PCT/US2010/054424
申请日：2010-10-28
申请人： THE TRUSTEES OF COLUMBIA UNIVERSITY IN THE CITY OF NEW YORK , SONY CORPORATION , GU, Jinwei , HITOMI, Yasunobu , MITSUNAGA, Tomoo , NAYAR, Shree, K.
发明人： GU, Jinwei , HITOMI, Yasunobu , MITSUNAGA, Tomoo , NAYAR, Shree, K.
IPC分类号： G06K9/00
CPC分类号： H04N7/002 , G06T5/003 , G06T2207/20201 , H04N5/2329 , H04N5/2353 , H04N5/3532 , H04N5/3535 , H04N5/35554 , H04N5/374 , H04N5/378 , H04N7/00
摘要： Methods and systems for coded rolling shutter are provided. In accordance with some embodiments, methods and system are provided that control the readout timing and exposure length for each row of a pixel array in an image sensor, thereby flexibly sampling the three-dimensional space-time value of a scene and capturing sub-images that effectively encode motion and dynamic range information within a single captured image.
摘要翻译：提供编码滚动快门的方法和系统。根据一些实施例，提供了控制图像传感器中的像素阵列的每行的读出定时和曝光长度的方法和系统，从而灵活地对场景的三维时空值进行采样并捕获子图像其在单个捕获图像内有效地编码运动和动态范围信息。

10. 发明申请

WO2009120718A1 METHODS, SYSTEMS, AND MEDIA FOR CONTROLLING DEPTH OF FIELD IN IMAGES 审中-公开
标题翻译：用于控制图像深度的方法，系统和媒体
公开(公告)号：WO2009120718A1
公开(公告)日：2009-10-01
申请号：PCT/US2009/038140
申请日：2009-03-24
申请人： THE TRUSTEES OF COLUMBIA UNIVERSITY IN THE CITY OF NEW YORK , NAYAR, Shree, K. , NAGAHARA, Hajime , KUTHIRUMMAL, Sujit , ZHOU, Changyin
发明人： NAYAR, Shree, K. , NAGAHARA, Hajime , KUTHIRUMMAL, Sujit , ZHOU, Changyin
IPC分类号： G03B13/00
CPC分类号： G03B13/00 , G02B27/0075 , H04N5/23212 , H04N5/23229 , H04N5/2356 , H04N2101/00
摘要： Methods, systems, and media for controlling depth of field in images are provided. In some embodiments, an image detector is translated so that an image incident on the image detector changes focus during at least a portion of an integration period of the image detector. An image is then captured at the image detector during the integration period.
摘要翻译：提供了用于控制图像中景深的方法，系统和媒体。在一些实施例中，图像检测器被平移，使得入射到图像检测器上的图像在图像检测器的积分周期的至少一部分期间改变焦点。然后在积分期间在图像检测器处捕获图像。

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