专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

101. 发明申请

US20090290810A1 MATTE-BASED VIDEO RESTORATION 有权
标题翻译：基于MATTE的视频恢复
公开(公告)号：US20090290810A1
公开(公告)日：2009-11-26
申请号：US12124158
申请日：2008-05-21
申请人： Sing Bing Kang , Jiading Gai
发明人： Sing Bing Kang , Jiading Gai
IPC分类号： G06K9/40
CPC分类号： G06T5/005 , G06T5/20 , G06T5/50 , G06T2207/10016 , G06T2207/10024 , G06T2207/20028 , G06T2207/20182 , H04N9/11
摘要： Matte-based video restoration technique embodiments are presented which model spatio-temporally varying film wear artifacts found in digitized copies of film media. In general, this is accomplished by employing residual color information in recovering of artifact mattes. To this end, the distributions of artifact colors and their fractional contribution to each pixel of each frame being considered are extracted based on color information from the spatial and temporal neighborhoods of the pixel. The extracted information can then be used to restore the video by removing the artifacts.
摘要翻译：提出了基于Matte的视频恢复技术实施例，其模型在电影媒体的数字化副本中发现的时空变化的电影磨损伪像。一般来说，这是通过使用残余颜色信息来恢复伪像哑光来实现的。为此，基于来自该像素的空间和时间邻域的颜色信息，提取伪像颜色的分布及其对所考虑的每帧的每个像素的分数贡献。所提取的信息然后可以用于通过去除伪影来恢复视频。

102. 发明授权

US07599547B2 Symmetric stereo model for handling occlusion 失效
标题翻译：用于处理遮挡的对称立体模型
公开(公告)号：US07599547B2
公开(公告)日：2009-10-06
申请号：US11289907
申请日：2005-11-30
申请人： Jian Sun , Yin Li , Sing Bing Kang , Heung-Yeung Shum
发明人： Jian Sun , Yin Li , Sing Bing Kang , Heung-Yeung Shum
IPC分类号： G06K9/00 , G06T15/00 , G01C3/14
CPC分类号： G06K9/32
摘要： The present symmetric stereo matching technique provides a method for iteratively estimating a minimum energy for occlusion and disparity using belief propagation. The minimum energy is based on an energy minimization framework in which a visibility constraint is embedded. By embedding the visibility constraint, the present symmetric stereo matching technique treats both images equally, instead of treating one as a reference image. The visibility constraint ensures that occlusion in one view and the disparity in another view are consistent.
摘要翻译：本对称立体匹配技术提供了一种使用置信传播迭代估计遮挡和视差的最小能量的方法。最小能量基于嵌入可见性约束的能量最小化框架。通过嵌入可见度约束，本对称立体匹配技术可以平等对待两个图像，而不是将其视为参考图像。可见性约束确保一个视图中的遮挡和另一个视图中的视差是一致的。

103. 发明授权

US07492927B2 Facial image processing methods and systems 有权
标题翻译：面部图像处理方法和系统
公开(公告)号：US07492927B2
公开(公告)日：2009-02-17
申请号：US10846308
申请日：2004-05-14
申请人： Stephen Marschner , Brian K. Guenter , Sashi Raghupathy , Kirk Olynyk , Sing Bing Kang
发明人： Stephen Marschner , Brian K. Guenter , Sashi Raghupathy , Kirk Olynyk , Sing Bing 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.
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。

104. 发明申请

US20080309660A1 THREE DIMENSIONAL RENDERING OF DISPLAY INFORMATION 有权
标题翻译：显示信息的三维渲染
公开(公告)号：US20080309660A1
公开(公告)日：2008-12-18
申请号：US11761604
申请日：2007-06-12
申请人： Joe Bertolami , Robert M. Craig , Dax Hawkins , Sing Bing Kang , Jonathan E. Lange
发明人： Joe Bertolami , Robert M. Craig , Dax Hawkins , Sing Bing Kang , Jonathan E. Lange
IPC分类号： G06T15/00
CPC分类号： A63F13/525 , A63F13/10 , A63F2300/66 , G06T15/20 , H04N13/275
摘要： Game data is rendered in three dimensions in the GPU of a game console. A left camera view and a right camera view are generated from a single camera view. The left and right camera positions are derived as an offset from a default camera. The focal distance of the left and right cameras is infinity. A game developer does not have to encode dual images into a specific hardware format. When a viewer sees the two slightly offset images, the user's brain combines the two offset images into a single 3D image to give the illusion that objects either pop out from or recede into the display screen. In another embodiment, individual, private video is rendered, on a single display screen, for different viewers. Rather than rendering two similar offset images, two completely different images are rendered allowing each player to view only one of the images.
摘要翻译：游戏数据在游戏机的GPU中呈现三维。从单个摄像机视图生成左侧摄像机视图和右侧摄像机视图。左和右摄像机位置被派生为与默认摄像机的偏移量。左右相机的焦距为无穷远。游戏开发者不必将双重图像编码为特定的硬件格式。当观众看到两个轻微偏移的图像时，用户的大脑将两个偏移图像组合成单个3D图像，以给出对象从显示屏幕中弹出或退回到显示屏幕的错觉。在另一个实施例中，单独的专用视频在单个显示屏幕上被呈现给不同的观看者。而不是渲染两个相似的偏移图像，渲染两个完全不同的图像，允许每个播放器仅查看其中一个图像。

105. 发明申请

US20080298712A1 IMAGE SHARPENING WITH HALO SUPPRESSION 有权
标题翻译：图像与HALO抑制相似
公开(公告)号：US20080298712A1
公开(公告)日：2008-12-04
申请号：US11755661
申请日：2007-05-30
申请人： Sing Bing Kang
发明人： Sing Bing Kang
IPC分类号： G06K9/40
CPC分类号： G06T5/004 , G06T2207/20192 , H04N5/23229 , H04N2201/00
摘要： An image sharpening technique with halo suppression is presented. Generally, one implementation of this technique completely suppresses the haloing effect typically caused by image sharpening by restricting values to within the local minimum and maximum intensities of the unsharpened image. Thus, if the sharpened value is below the local minimum, it is replaced with the local minimum. Similarly, the local maximum is taken if the sharpened value exceeds it. In other implementations of the technique, haloing caused by image sharpening is suppressed but not completely eliminated, thereby producing a subtle haloing effect.
摘要翻译：提出了具有光晕抑制的图像锐化技术。通常，该技术的一个实现完全抑制通常通过将值限制在未钝化图像的局部最小和最大强度内的图像锐化引起的晕圈效应。因此，如果锐化值低于局部最小值，则将其替换为局部最小值。类似地，如果锐化值超过本地值，则采用局部最大值。在该技术的其他实施方式中，由图像锐化引起的晕圈被抑制但不能完全消除，从而产生微妙的晕圈效应。

106. 发明申请

US20080112642A1 Video Completion By Motion Field Transfer 有权
标题翻译：视频完成通过运动场传输
公开(公告)号：US20080112642A1
公开(公告)日：2008-05-15
申请号：US11559861
申请日：2006-11-14
申请人： Yasuyuki Matsushita , Sing Bing Kang , Xiaoou Tang , Takaaki Shiratori
发明人： Yasuyuki Matsushita , Sing Bing Kang , Xiaoou Tang , Takaaki Shiratori
IPC分类号： G06K9/40
CPC分类号： G06T5/005 , G06T5/20 , G06T5/50 , G06T2207/10016 , G06T2207/20016
摘要： Systems and methods for video completion by motion field transfer are described. In one aspect, a spatio-temporal target patch of an input video data sequence is filled in or replaced by motion field transfer from a spatio-temporal source patch of the input video data sequence. Color is propagated to corresponding portions of the spatio-temporal target patch by treating the transferred motion information as directed edges These motion field transfer and color propagation operations result in a video completed spatio-temporal target patch. The systems and methods present the video data sequence, which now includes the video completed spatio-temporal target patch, to user for viewing.
摘要翻译：描述了通过运动场传输进行视频完成的系统和方法。在一个方面，输入视频数据序列的时空目标贴片由输入视频数据序列的时空源片段填充或由运动场传输代替。通过将转移的运动信息作为有向边缘进行处理，将颜色传播到时空目标贴片的相应部分。这些运动场转移和颜色传播操作导致视频完成的时空目标贴片。系统和方法呈现视频数据序列，其现在包括视频完成的时空目标补丁，供用户观看。

107. 发明授权

US07152024B2 Facial image processing methods and systems 有权
公开(公告)号：US07152024B2
公开(公告)日：2006-12-19
申请号：US11217540
申请日：2005-09-01
申请人： Stephen Marschner , Brian K. Guenter , Sashi Raghupathy , Kirk Olynyk , Sing Bing Kang
发明人： Stephen Marschner , Brian K. Guenter , Sashi Raghupathy , Kirk Olynyk , Sing Bing Kang
IPC分类号： G06K9/00 , G06F7/60
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.

108. 发明授权

US07046401B2 Camera-based document scanning system using multiple-pass mosaicking 有权
公开(公告)号：US07046401B2
公开(公告)日：2006-05-16
申请号：US09872725
申请日：2001-06-01
申请人： Frederic Dufaux , Sing Bing Kang , Robert Alan Ulichney
发明人： Frederic Dufaux , Sing Bing Kang , Robert Alan Ulichney
IPC分类号： H04N1/387 , H04N1/04 , G06K9/48 , G06K9/40 , G06K9/00
CPC分类号： H04N1/3876 , G06K9/20 , G06T3/0075 , G06T5/006 , G06T7/207 , G06T7/30 , H04N1/195 , H04N1/19594 , H04N2201/0414 , H04N2201/0436
摘要： A camera-based document scanning system produces electronic versions of documents, based on a plurality of images of discrete portions of the documents. The system compares each pair of consecutive images and derives motion parameters that indicate the relative motion between each pair of consecutive images. The system utilizes the derived motion parameters to align and merge each image with respect to the previous images, thereby building a single, mosaic image of the document. In the illustrative embodiment, the motion parameters are derived by minimizing a sum of squared differences equation on a pixel-by-pixel basis.

109. 发明授权

US06850872B1 Facial image processing methods and systems 有权
标题翻译：面部图像处理方法和系统
公开(公告)号：US06850872B1
公开(公告)日：2005-02-01
申请号：US09652600
申请日：2000-08-30
申请人： Stephen Marschner , Brian K. Guenter , Sashi Raghupathy , Kirk Olynyk , Sing Bing Kang
发明人： Stephen Marschner , Brian K. Guenter , Sashi Raghupathy , Kirk Olynyk , Sing Bing Kang
IPC分类号： G06T1/00 , G06F7/60 , G06F9/455 , G06F17/10 , G06K9/00 , G06K9/46 , G06T7/00 , G06T15/50 , G06T15/60 , G06F101/00
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.
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。

110. 发明授权

US06256058B1 Method for simultaneously compositing a panoramic image and determining camera focal length 失效
标题翻译：同时合成全景图像和确定相机焦距的方法
公开(公告)号：US06256058B1
公开(公告)日：2001-07-03
申请号：US08660704
申请日：1996-06-06
申请人： Sing Bing Kang , Richard S. Weiss
发明人： Sing Bing Kang , Richard S. Weiss
IPC分类号： H04N5225
CPC分类号： H04N5/23238 , H04N5/2624
摘要： In a computerized image processing system, a camera acquires a set of images of a scene while rotating the camera about an axis passing through an optical center of the camera. The images of the set overlap each other. An initial estimate of the focal length of the camera is made. The initial focal length can be any reasonable focal length. Using the initial estimate of the focal length, the set of images are composited in a memory to determine an estimated initial composited length. A next best estimate of the focal length is derived from the initial estimated composited length. The set of images are recomposed using the next best focal length estimate. This process is iterated until the absolute difference between the successive estimates of the focal length is less than a predetermined threshold to calibrate the camera. In addition, the process of compositing the set of images can use a weighted interpolation scheme to reduce the blurring effects caused by noise and digitization effects and incorrect focal length.
摘要翻译：在计算机化图像处理系统中，摄像机围绕通过照相机的光学中心的轴旋转摄像机时，照相机获取场景的一组图像。集合的图像彼此重叠。进行摄像机焦距的初始估计。初始焦距可以是任何合理的焦距。使用焦距的初始估计，将图像集合在存储器中以确定估计的初始合成长度。焦距的下一个最佳估计来自初始估计的合成长度。使用下一个最佳焦距估计重组该组图像。迭代该过程直到焦距的连续估计之间的绝对差小于预定阈值以校准相机。另外，合成图像集合的过程可以使用加权插值方案来减少由噪声和数字化效应引起的模糊效应和不正确的焦距。

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