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

WO2013106734A1 SYSTEMS AND METHODS FOR VIDEO DENOISING 审中-公开
标题翻译：用于视频放像的系统和方法
公开(公告)号：WO2013106734A1
公开(公告)日：2013-07-18
申请号：PCT/US2013/021269
申请日：2013-01-11
申请人： HUAWEI TECHNOLOGIES CO., LTD. , ZHANG, Dong-Qing , WANG, Bo , YU, Hong Heather
发明人： ZHANG, Dong-Qing , WANG, Bo , YU, Hong Heather
IPC分类号： G06K9/40
CPC分类号： H04N19/55 , H04N19/80
摘要： An embodiment robust spatial-temporal hybrid filter takes into account the pixel data reliability and has the capability of estimating pixel data statistics for more robust spatial/temporal filter switching and more reliable filtering results.
摘要翻译：实施例鲁棒的空间 - 时间混合滤波器考虑了像素数据的可靠性，并且具有估计像素数据统计以获得更强大的空间/时间滤波器切换和更可靠的滤波结果的能力。

2. 发明申请

WO2012033963A2 METHODS AND APPARATUS FOR DECODING VIDEO SIGNALS USING MOTION COMPENSATED EXAMPLE-BASED SUPER-RESOLUTION FOR VIDEO COMPRESSION 审中-公开
标题翻译：使用运动补偿的基于示例的超分辨率来解码视频信号的方法和装置用于视频压缩
公开(公告)号：WO2012033963A2
公开(公告)日：2012-03-15
申请号：PCT/US2011/050915
申请日：2011-09-09
申请人： THOMSEN LISCENSING , ZHANG, Dong-Qing , JACOB, Mithun George , BHAGAVATHY, Sitaram
发明人： ZHANG, Dong-Qing , JACOB, Mithun George , BHAGAVATHY, Sitaram
IPC分类号： G06T7/20
CPC分类号： H04N19/85 , H04N19/132 , H04N19/14 , H04N19/176 , H04N19/44 , H04N19/46 , H04N19/587 , H04N19/61
摘要： Methods and apparatus are provided for decoding video signals using motion compensated example-based super-resolution for video compression. An apparatus includes an example-based super-resolution processor (820) for receiving one or more high resolution replacement patch pictures generated from a static version of an input video sequence having motion, and performing example-based super-resolution to generate a reconstructed version of the static version of the input video sequence from the one or more high resolution replacement patch pictures. The reconstructed version of the static version of the input video sequence includes a plurality of pictures. The apparatus further includes an inverse image warper (830) for receiving motion parameters for the input video sequence, and performing an inverse picture warping process based on the motion parameters to transform one or more of the plurality of pictures to generate a reconstruction of the input video sequence having the motion.
摘要翻译：提供了使用用于视频压缩的基于运动补偿的基于示例的超分辨率来解码视频信号的方法和装置。一种装置包括基于示例的超分辨率处理器（820），用于接收从具有运动的输入视频序列的静态版本生成的一个或多个高分辨率替换贴片图像，以及执行基于示例的超分辨率以生成重建版本的静态版本的输入视频序列从一个或多个高分辨率替换补丁图片。输入视频序列的静态版本的重建版本包括多个图片。该装置还包括用于接收输入视频序列的运动参数的逆图像整形器（830），以及基于运动参数执行逆图像扭曲处理，以转换多个图像中的一个或多个以生成输入的重建具有运动的视频序列。

3. 发明申请

WO2011142733A1 A CONFIGURABLE COMPUTING ARCHITECTURE 审中-公开
标题翻译：可配置的计算机架构
公开(公告)号：WO2011142733A1
公开(公告)日：2011-11-17
申请号：PCT/US2010/001390
申请日：2010-05-11
申请人： THOMSON LICENSING , ZHANG, Dong-Qing , JOSHI, Rajan, Laxman
发明人： ZHANG, Dong-Qing , JOSHI, Rajan, Laxman
IPC分类号： G06F9/50
CPC分类号： G06F9/541 , G06F9/545
摘要： A configurable computing system for parallel processing of software applications includes an environment abstraction layer (EAL) for abstracting low-level functions to the software applications; a space layer including a distributed data structure; and a kernel layer including a job scheduler for executing parallel processing programs constructing the software applications according to a configurable mode.
摘要翻译：用于并行处理软件应用的可配置计算系统包括用于将软件应用的低级功能抽象的环境抽象层（EAL）; 包括分布式数据结构的空间层; 以及内核层，其包括作业调度器，用于根据可配置模式执行构建软件应用的并行处理程序。

4. 发明申请

WO2009151424A1 SYSTEM AND METHOD FOR MARKING A STEREOSCOPIC FILM 审中-公开
标题翻译：用于标记立体电影的系统和方法
公开(公告)号：WO2009151424A1
公开(公告)日：2009-12-17
申请号：PCT/US2008/007508
申请日：2008-06-13
申请人： THOMSON LICENSING , YOON, Youngshik , IZZAT, Izzat , ZHANG, Dong-Qing
发明人： YOON, Youngshik , IZZAT, Izzat , ZHANG, Dong-Qing
IPC分类号： H04N13/00
CPC分类号： G06K9/00 , G03B35/18 , G06T1/0028 , H04N13/10
摘要： A system and method for marking a stereoscopic film with colors are provided. The system and method provides for marking a left image with a mark and a right image with a mark having complementary colors, wherein upon viewing, the marks are not visible under certain conditions. The system and method provide for acquiring (202) a stereoscopic image, the stereoscopic image including a first image and a second image, applying (204) a first mark to the first image in a predetermined location, the first mark having a first color, and applying (206) a second mark to the second image in substantially the same predetermined location as in the first image, the second mark having a second color that is different than the first color of the first mark, wherein when viewed in three-dimensional mode, the first mark and the second mark combine into a single mark of one color.
摘要翻译：提供了一种用于用彩色标记立体薄膜的系统和方法。该系统和方法提供用标记和具有补色标记的右图像标记左图像，其中在观看时，标记在某些条件下是不可见的。所述系统和方法提供用于获取（202）立体图像，所述立体图像包括第一图像和第二图像，在预定位置对第一图像应用（204）第一标记，所述第一标记具有第一颜色，以及在与所述第一图像基本相同的预定位置中向所述第二图像施加（206）第二标记，所述第二标记具有与所述第一标记的第一颜色不同的第二颜色，其中当以三维模式，第一个标记和第二个标记组合成一个颜色的单个标记。

5. 发明申请

WO2009005497A1 APPARATUS AND METHOD FOR REDUCING ARTIFACTS IN IMAGES 审中-公开
标题翻译：用于减少图像中的艺术家的装置和方法
公开(公告)号：WO2009005497A1
公开(公告)日：2009-01-08
申请号：PCT/US2007/015205
申请日：2007-06-29
申请人： THOMSON LICENSING , GUO, Ju , ZHANG, Dong-Qing
发明人： GUO, Ju , ZHANG, Dong-Qing
IPC分类号： G06T5/00
CPC分类号： H04N9/646 , G06T7/11 , G06T7/187 , G06T7/90 , G06T2207/10016 , G06T2207/10024
摘要： An apparatus and method of the present disclosure provides an automatic banding region detection function for detecting an image region that has a smooth linear transition of color intensity and is prone to have banding artifacts in image processing. The apparatus and method use a parametric model based approach to detect the banding region. The apparatus and method provide for segmenting at least one first image into at least one homogeneous color region (304), estimating the linear transition of color intensity for the at least one homogeneous color region (308), and if the linear transition of color intensity is substantially smooth, classifying the at least one homogenous color region as a banding region (310).
摘要翻译：本公开的装置和方法提供了一种自动条带区域检测功能，用于检测具有光强度的平滑线性跃迁的图像区域，并且在图像处理中容易具有带状伪影。该装置和方法使用基于参数模型的方法来检测条带区域。所述装置和方法提供将至少一个第一图像分割成至少一个均匀颜色区域（304），估计所述至少一个均匀颜色区域（308）的颜色强度的线性转变，以及如果颜色强度的线性转变基本上平滑，将至少一个均匀颜色区域分类为条带区域（310）。

6. 发明申请

WO2008063170A1 SYSTEM AND METHOD FOR COMPOSITING 3D IMAGES 审中-公开
标题翻译：用于组合3D图像的系统和方法
公开(公告)号：WO2008063170A1
公开(公告)日：2008-05-29
申请号：PCT/US2006/045029
申请日：2006-11-20
申请人： THOMSON LICENSING , BENITEZ, Ana Belen , ZHANG, Dong-Qing , FANCHER, Jim Arthur
发明人： BENITEZ, Ana Belen , ZHANG, Dong-Qing , FANCHER, Jim Arthur
IPC分类号： G06T15/20
CPC分类号： G06T19/20 , G06T2219/2004 , H04N13/156 , H04N13/178
摘要： A system and method for compositing 3D images that combines parts of or at least a portion of two or more images having 3D properties to create a 3D image. The system and method of the present disclosure provides for acquiring at least two three-dimensional (3D) images (202, 204), obtaining metadata (e.g., lighting, geometry, and object information) relating to the at least two 3D images (206, 208), mapping the metadata of the at least two 3D images into a single 3D coordinate system, and compositing a portion of each of the at least two 3D images into a single 3D image (214). The single 3D image can be rendered into a desired format (e.g., stereo image pair) (218). The system and method can associate the rendered output with relevant metadata (e.g., interocular distance for stereo image pairs) (218).
摘要翻译：一种用于合成3D图像的系统和方法，其组合具有3D属性的两个或更多个图像的部分或至少一部分以创建3D图像。本公开的系统和方法提供用于获取至少两个三维（3D）图像（202,204），获得与至少两个3D图像（206）有关的元数据（例如，照明，几何和对象信息），208），将所述至少两个3D图像的元数据映射到单个3D坐标系中，以及将所述至少两个3D图像中的每一个的一部分合成为单个3D图像（214）。单个3D图像可以呈现为期望的格式（例如，立体图像对）（218）。系统和方法可以将所渲染的输出与相关的元数据（例如，立体图像对的眼间距离）相关联（218）。

7. 发明申请

WO2012078126A1 SYSTEM AND METHOD FOR TRINOCULAR DEPTH ACQUISITION WITH TRIANGULAR SENSOR 审中-公开
标题翻译：用三角波传感器进行三角波深度采集的系统和方法
公开(公告)号：WO2012078126A1
公开(公告)日：2012-06-14
申请号：PCT/US2010/003122
申请日：2010-12-08
申请人： THOMSON LICENSING , ZHANG, Dong-Qing , ZHAI, Jiefu , WANG, Zhe
发明人： ZHANG, Dong-Qing , ZHAI, Jiefu , WANG, Zhe
IPC分类号： H04N13/00 , G06T7/00
CPC分类号： H04N13/25 , G06T7/55 , G06T2207/20088 , H04N13/243
摘要： A depth acquisition system utilizes at least three sensors with at least one sensor in a non-colinear configuration to increase depth information. This configuration provides both vertical and horizontal depth information to be combined to enhance image quality, especially in three-dimensional image gathering. Vertical sensor pairs aid in determining disparities for horizontal edges and make depth estimations for horizontal edges more accurate.
摘要翻译：深度采集系统利用至少三个具有非共线配置中的至少一个传感器的传感器来增加深度信息。该配置提供要组合的垂直和水平深度信息以增强图像质量，特别是在三维图像采集中。垂直传感器对有助于确定水平边缘的差异，并使水平边缘的深度估计更准确。

8. 发明申请

WO2012033972A1 METHODS AND APPARATUS FOR PRUNING DECISION OPTIMIZATION IN EXAMPLE-BASED DATA PRUNING COMPRESSION 审中-公开
标题翻译：用于在基于示例的数据预处理压缩中进行决策优化的方法和装置
公开(公告)号：WO2012033972A1
公开(公告)日：2012-03-15
申请号：PCT/US2011/050925
申请日：2011-09-09
申请人： THOMSON LICENSING , HAO, Qiang , ZHANG, Dong-Qing
发明人： HAO, Qiang , ZHANG, Dong-Qing
IPC分类号： H04N7/26 , H04N7/46
CPC分类号： H04N19/85 , H04N19/132 , H04N19/147 , H04N19/176 , H04N19/19 , H04N19/46 , H04N19/59
摘要： Method and apparatus for encoding a picture in a video sequence are disclosed. An apparatus includes a patch library creator (145) for creating a first patch library from an original version of the picture and a second patch library from a reconstructed version of the picture. Each of the libraries includes a plurality of high resolution replacement patches for replacing one or more pruned blocks during a recovery of a pruned version of the picture. A pruner (105) generates the pruned version from the first patch library, and decides whether to respectively replace original blocks with pruned blocks responsive to a comparison between a first rate-distortion estimate and a second rate-distortion estimate. The estimates are based on both a distortion component and a bitrate component. A metadata generator (135) generates metadata from the second patch library. The metadata is for recovering the pruned version. An encoder (110, 135) encodes the pruned version and the metadata.
摘要翻译：公开了一种用于对视频序列中的图像进行编码的方法和装置。一种装置包括补丁库创建器（145），用于从图像的原始版本创建第一补丁库，以及从图像的重建版本创建第二补丁库。每个库包括多个高分辨率替换补丁，用于在恢复修剪版本的图片期间替换一个或多个修剪的块。修剪器（105）从第一补丁库生成修剪版本，并且响应于第一速率失真估计和第二速率失真估计之间的比较，决定是否分别用修剪的块替换原始块。估计基于失真分量和比特率分量。元数据生成器（135）从第二补丁库生成元数据。元数据用于恢复修剪版本。编码器（110,135）对修剪的版本和元数据进行编码。

9. 发明申请

WO2012033970A1 ENCODING OF A PICTURE IN A VIDEO SEQUENCE BY EXAMPLE - BASED DATA PRUNING USING INTRA- FRAME PATCH SIMILARITY 审中-公开
标题翻译：通过基于实例的数据调制在视频序列中编码图像使用帧内匹配相似度
公开(公告)号：WO2012033970A1
公开(公告)日：2012-03-15
申请号：PCT/US2011/050923
申请日：2011-09-09
申请人： THOMSON LICENSING , ZHANG, Dong-Qing , BHAGAVATHY, Sitaram , HE, Shan
发明人： ZHANG, Dong-Qing , BHAGAVATHY, Sitaram , HE, Shan
IPC分类号： H04N7/26 , H04N7/50
CPC分类号： H04N19/85 , G06T5/001 , H04N19/132 , H04N19/14 , H04N19/176 , H04N19/196 , H04N19/44 , H04N19/46 , H04N19/463 , H04N19/587 , H04N19/59 , H04N19/593 , H04N19/61 , H04N19/97
摘要： Method and apparatus for encoding a picture in video sequence are disclosed. An apparatus includes a library creator (145) for creating a first library from an original version of the picture and a second library from a reconstructed version of the picture. Each library includes high resolution replacement patches for replacing pruned blocks during a recovery of a pruned version of the picture. A pruner (105) generates the pruned version from the first library. A metadata generator (135) generates metadata from the second library for recovering the pruned version. An encoder (110, 135) encodes the pruned version and metadata. The first library includes patch clusters. The pruned version is generated by dividing the original version into overlapping blocks and searching for candidate patch clusters for each block. A patch dependency graph having nodes and edges is used for the searching. Each node represents a respective block, and each edge represents a respective dependency of the respective block.
摘要翻译：公开了以视频序列编码图像的方法和装置。一种装置包括用于从图像的原始版本创建第一库的库创建器（145）和来自图像的重构版本的第二库。每个库包括高分辨率替换补丁，用于在恢复修剪版本的图片期间替换已修剪的块。修剪器（105）从第一个库生成修剪版本。元数据生成器（135）从第二库生成元数据以恢复修剪版本。编码器（110,135）对修剪的版本和元数据进行编码。第一个库包括补丁集群。修剪版本通过将原始版本划分为重叠块并搜索每个块的候选修补程序簇来生成。具有节点和边缘的补丁依赖图用于搜索。每个节点表示相应的块，并且每个边缘表示相应块的相应依赖性。

10. 发明申请

WO2012033967A1 VIDEO DECODING USING BLOCK- BASED MIXED - RESOLUTION DATA PRUNING 审中-公开
标题翻译：使用基于块的混合视频解码 - 分辨率数据调制
公开(公告)号：WO2012033967A1
公开(公告)日：2012-03-15
申请号：PCT/US2011/050920
申请日：2011-09-09
申请人： THOMSON LICENSING , ZHANG, Dong-Qing
发明人： ZHANG, Dong-Qing
IPC分类号： H04N7/26 , H04N7/50
CPC分类号： H04N19/00945 , H04N19/132 , H04N19/134 , H04N19/14 , H04N19/176 , H04N19/44 , H04N19/46 , H04N19/48 , H04N19/587 , H04N19/59 , H04N19/61 , H04N19/70 , H04N19/85 , H04N19/90
摘要： Method and apparatus are provided for recovering a pruned version of a picture in a video sequence is disclosed. An apparatus includes a pruned block identifier (610) for identifying one or more pruned blocks in the pruned version of the picture. The apparatus further includes a metadata decoder (615) for decoding metadata for recovering the pruned version of the picture. The metadata includes position information of the one or more replacement blocks. The apparatus also includes a block restorer (620) for respectively generating one or more replacement blocks for the one or more pruned blocks.
摘要翻译：公开了一种用于在视频序列中恢复图像的修剪版本的方法和装置。一种装置包括用于识别图像的修剪版本中的一个或多个修剪块的修剪块标识符（610）。该装置还包括用于解码用于恢复图像的修剪版本的元数据的元数据解码器（615）。元数据包括一个或多个替换块的位置信息。该装置还包括块恢复器（620），用于分别为一个或多个修剪块生成一个或多个替换块。

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