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. 发明授权

US06314211B1 Apparatus and method for converting two-dimensional image sequence into three-dimensional image using conversion of motion disparity into horizontal disparity and post-processing method during generation of three-dimensional image 有权
标题翻译：用于将二维图像序列转换为三维图像的装置和方法，其使用运动差异转换为水平视差，并且在生成三维图像时进行后处理
公开(公告)号：US06314211B1
公开(公告)日：2001-11-06
申请号：US09222713
申请日：1998-12-29
申请人： Man-bae Kim , Mun-sup Song , Do-kyoon Kim
发明人： Man-bae Kim , Mun-sup Song , Do-kyoon Kim
IPC分类号： G06K936
CPC分类号： G06K9/20 , G06K2209/40 , G06T7/579 , G06T7/97 , G06T2207/10012 , G06T2207/10021 , H04N13/111 , H04N13/167 , H04N13/189 , H04N13/221 , H04N13/239 , H04N13/261 , H04N13/286 , H04N13/341 , H04N13/398 , H04N19/597 , H04N2013/0081 , H04N2013/0085 , H04N2013/0092
摘要： An apparatus and a method for converting a two-dimensional image sequence into a three-dimensional image using a conversion of a motion disparity into a horizontal disparity and a post-processing method during the generation of a three-dimensional image are provided. The apparatus for converting a two-dimensional image sequence into a three-dimensional image according to the present invention includes a block motion measuring portion for measuring a motion vector for each block of a current image divided into blocks having a predetermined size using a previous image frame, a horizontal disparity generating portion for obtaining a horizontal disparity from the motion vector of each block according to the motion characteristic of the current image, an image generating portion for moving each block in a horizontal direction according to each horizontal disparity and generating a composite image corresponding to the current image, and an outputting portion for displaying a three-dimensional image formed of the current image and the composite image.
摘要翻译：提供了一种用于在生成三维图像期间将运动视差转换为水平视差和后处理方法将二维图像序列转换为三维图像的装置和方法。根据本发明的用于将二维图像序列转换成三维图像的装置包括块运动测量部分，用于使用先前图像测量分割成具有预定尺寸的块的当前图像的每个块的运动矢量帧，用于根据当前图像的运动特性从每个块的运动矢量获得水平视差的水平视差生成部分，用于根据每个水平视差移动水平方向上的每个块的图像生成部分，并且生成复合物对应于当前图像的图像，以及用于显示由当前图像和合成图像形成的三维图像的输出部分。

52. 发明授权

US09406164B2 Apparatus and method of multi-view rendering 有权
标题翻译：多视图渲染的装置和方法
公开(公告)号：US09406164B2
公开(公告)日：2016-08-02
申请号：US13556479
申请日：2012-07-24
申请人： Young-ihn Kho , Do-kyoon Kim , Tae-hyun Rhee , Min-su Ahn , Hee-sae Lee
发明人： Young-ihn Kho , Do-kyoon Kim , Tae-hyun Rhee , Min-su Ahn , Hee-sae Lee
IPC分类号： G06T15/00 , G06T15/20
CPC分类号： G06T15/205
摘要： Provided is an apparatus and method of multi-view rendering. A method of multi-view rendering includes rendering one or more 3D objects based on a first viewpoint, transforming pixel values of pixels of the first viewpoint, which are obtained by the rendering of the 3D objects, into pixel values of pixels based on a second viewpoint that is different from the first viewpoint, detecting an occlusion region that is a remaining region other than a region represented by the pixel values obtained by the transforming of the pixel values in an image based on the second viewpoint, and rendering the detected occlusion region based on the second viewpoint.
摘要翻译：提供了一种多视图渲染的装置和方法。多视图渲染的方法包括：基于第一视点来呈现一个或多个3D对象，将通过3D对象的呈现获得的第一视点的像素的像素值转换为基于第二视点的像素的像素值检测与第一视点不同的视点，检测作为除了通过基于第二视点对图像中的像素值进行变换而获得的像素值所表示的区域之外的剩余区域的遮挡区域，并且将检测到的遮挡区域基于第二观点。

53. 发明授权

US09235932B2 Method and apparatus to generate 3D volume-panorama image based on 3D volume images 有权
标题翻译：基于3D体积图像生成3D体积全景图像的方法和装置
公开(公告)号：US09235932B2
公开(公告)日：2016-01-12
申请号：US13552880
申请日：2012-07-19
申请人： Ouk Choi , Yong-sun Kim , Jung-ho Kim , Seong-deok Lee , Do-kyoon Kim
发明人： Ouk Choi , Yong-sun Kim , Jung-ho Kim , Seong-deok Lee , Do-kyoon Kim
IPC分类号： G06T17/00 , G06K9/46 , G06T19/00 , G06T7/00 , G06T3/40
CPC分类号： G06T19/00 , G06T3/4038 , G06T7/33 , G06T2207/10136 , G06T2207/30044
摘要： A method and apparatus to generate a volume-panorama image based on three-dimensional (3D) volume images is provided. A method of generating a volume-panorama image includes receiving pieces of image data of one or more volume images, extracting partial regions including one or more voxels from the volume images, determining a global conversion function representing a relationship of a conversion between a second volume image of the volume images and a first volume image of the volume images, the determined global conversion function being based on a conversion function representing a relationship of a conversion between one of the extracted partial regions of the second volume image and one of the extracted partial regions of the first volume image, and generating image data of a volume image to be combined with the first volume image from image data of the second volume image based on the determined global conversion function.
摘要翻译：提供了一种基于三维（3D）体积图像生成体积全景图像的方法和装置。一种产生体积全景图像的方法包括接收一个或多个体积图像的图像数据片段，从体积图像中提取包括一个或多个体素的部分区域，确定表示第二体积之间的转换关系的全局变换函数体积图像的图像和体积图像的第一体积图像，所确定的全局变换功能基于表示第二体积图像的提取的部分区域之一与所提取的部分之一之间的转换的关系的转换函数基于所确定的全局变换函数，从第二卷图像的图像数据生成要与第一卷图像组合的卷图像的图像数据。

54. 发明申请

US20130021341A1 METHOD AND APPARATUS TO GENERATE 3D VOLUME-PANORAMA IMAGE BASED ON 3D VOLUME IMAGES 有权
标题翻译：基于3D体积图像生成3D体积全景图像的方法和装置
公开(公告)号：US20130021341A1
公开(公告)日：2013-01-24
申请号：US13552880
申请日：2012-07-19
申请人： Ouk Choi , Yong-sun Kim , Jung-ho Kim , Seong-deok Lee , Do-kyoon Kim
发明人： Ouk Choi , Yong-sun Kim , Jung-ho Kim , Seong-deok Lee , Do-kyoon Kim
IPC分类号： G06T17/00
CPC分类号： G06T19/00 , G06T3/4038 , G06T7/33 , G06T2207/10136 , G06T2207/30044
摘要： A method and apparatus to generate a volume-panorama image based on three-dimensional (3D) volume images is provided. A method of generating a volume-panorama image includes receiving pieces of image data of one or more volume images, extracting partial regions including one or more voxels from the volume images, determining a global conversion function representing a relationship of a conversion between a second volume image of the volume images and a first volume image of the volume images, the determined global conversion function being based on a conversion function representing a relationship of a conversion between one of the extracted partial regions of the second volume image and one of the extracted partial regions of the first volume image, and generating image data of a volume image to be combined with the first volume image from image data of the second volume image based on the determined global conversion function.
摘要翻译：提供了一种基于三维（3D）体积图像生成体积全景图像的方法和装置。一种产生体积全景图像的方法包括接收一个或多个体积图像的图像数据片段，从体积图像中提取包括一个或多个体素的部分区域，确定表示第二体积之间的转换关系的全局变换函数体积图像的图像和体积图像的第一体积图像，所确定的全局变换功能基于表示第二体积图像的提取的部分区域之一与所提取的部分之一之间的转换的关系的转换函数基于所确定的全局变换函数，从第二卷图像的图像数据生成要与第一卷图像组合的卷图像的图像数据。

55. 发明授权

US08155386B2 Method and apparatus for obtaining depth information 有权
标题翻译：获取深度信息的方法和装置
公开(公告)号：US08155386B2
公开(公告)日：2012-04-10
申请号：US12081501
申请日：2008-04-16
申请人： Jae-young Sim , Do-kyoon Kim , Kee-chang Lee
发明人： Jae-young Sim , Do-kyoon Kim , Kee-chang Lee
IPC分类号： G06K9/00 , G06K9/34
CPC分类号： G06T7/50 , G06T2207/10028
摘要： A method and apparatus for obtaining depth information are provided. The method includes calculating a relative depth value between a first color pixel and a second color pixel based on values of color pixels of a color image, and calculating a depth value of a second depth pixel that belongs to a depth image corresponding to the color image, matches the second color pixel, and does not have the depth value, based on the calculated relative depth value and a depth value of a first depth value that belongs to the depth image, matching the first color pixel, and has the depth value thereof.
摘要翻译：提供一种获取深度信息的方法和装置。该方法包括基于彩色图像的彩色像素的值来计算第一颜色像素和第二彩色像素之间的相对深度值，以及计算属于与彩色图像相对应的深度图像的第二深度像素的深度值基于计算出的相对深度值和属于深度图像的第一深度值的深度值，匹配第二颜色像素，并且不具有深度值，并且具有深度值。

56. 发明授权

US07171060B2 Method of perceptual 3D shape description and method and apparatus for searching 3D graphics model database using the description method 有权
标题翻译：感知3D形状描述的方法和使用描述方法搜索3D图形模型数据库的方法和装置
公开(公告)号：US07171060B2
公开(公告)日：2007-01-30
申请号：US10727660
申请日：2003-12-05
申请人： In-kyu Park , Do-kyoon Kim , Sang-uk Lee , Il-dong Yun , Duck-hoon Kim
发明人： In-kyu Park , Do-kyoon Kim , Sang-uk Lee , Il-dong Yun , Duck-hoon Kim
IPC分类号： G06K9/54 , G06K9/00 , G06T15/00
CPC分类号： G06T17/00 , G06T2210/61
摘要： A method of perceptual 3-dimensional (3D) shape description and a method and apparatus for searching a perceptual 3D graphics model database established using the description method are provided. The description method includes: generating nodes that respectively correspond to parts of a part-based representation of a 3D shape model, the nodes including unary attributes of the parts; generating edges that include relational attributes between the nodes; and generating an attributed relational graph of the 3D shape model that is comprised of the nodes and the edges. The search method includes: receiving a predetermined 3D graphics model; transforming the received 3D graphics model into a perceptual 3D shape descriptor; and comparing the perceptual 3D shape descriptor with each of the perceptual 3D graphics models stored in the database to retrieve the 3D graphic models that are similar to the perceptual 3D shape descriptor. The searching apparatus includes: a query input unit that receives a query that is a 3D graphics model; a model/shape descriptor transforming unit that transforms the 3D graphic model received as the query into a perceptual 3D shape descriptor; a matching unit that compares the perceptual 3D shape descriptor with each of the perceptual 3D graphics models stored in the database to retrieve the models that are similar to the perceptual 3D shape descriptor; and a model output unit that outputs the retrieved model. A query by sketch or a query by editing is available, and the models that are similar to a query can be more accurately retrieved due to a double earth mover's distance method used to match query and model graphs.
摘要翻译：提供一种感知三维（3D）形状描述的方法以及用于搜索使用描述方法建立的感知3D图形模型数据库的方法和装置。描述方法包括：生成分别对应于3D形状模型的基于部分的表示的部分的节点，所述节点包括部分的一元属性; 生成包括节点之间的关系属性的边; 并且生成由节点和边缘组成的3D形状模型的归属关系图。搜索方法包括：接收预定的3D图形模型; 将接收的3D图形模型转换为感知3D形状描述符; 以及将感知3D形状描述符与存储在数据库中的每个感知3D图形模型进行比较，以检索类似于感知3D形状描述符的3D图形模型。搜索装置包括：接收作为3D图形模型的查询的查询输入单元; 将作为查询接收到的3D图形模型变换为感知3D形状描述符的模型/形状描述符变换单元; 匹配单元，其将感知3D形状描述符与存储在数据库中的每个感知3D图形模型进行比较，以检索类似于感知3D形状描述符的模型; 以及输出所检索的模型的模型输出单元。通过草图查询或通过编辑进行查询是可用的，并且由于用于匹配查询和模型图的双土动员的距离方法，可以更准确地检索与查询类似的模型。

57. 发明授权

US06898320B2 Method for processing nodes in 3D scene and apparatus thereof 有权
标题翻译：用于处理3D场景中的节点的方法及其装置
公开(公告)号：US06898320B2
公开(公告)日：2005-05-24
申请号：US09805562
申请日：2001-03-14
申请人： Mahn-jin Han , Sung-jin Kim , Euee-seon Jang , Do-kyoon Kim
发明人： Mahn-jin Han , Sung-jin Kim , Euee-seon Jang , Do-kyoon Kim
IPC分类号： G06T17/00 , G06T17/20 , H04N1/41 , H04N19/00 , H04N19/20 , H04N19/597 , G06K9/36
CPC分类号： G06T17/20
摘要： A method for processing nodes in 3-dimensional (3D) scene and an apparatus thereof are provided. The method includes the steps of identifying a 3D mesh node having 3D mesh information representing a 3D shape which is formed by constructing faces from vertices among nodes contained in a 3D scene to be processed; and encoding or decoding the identified 3D mesh node. Also, the method includes the step of transmitting or storing the 3D mesh information of the encoded 3D mesh node through an independent stream separate from the 3D scene description stream. According to the method, a node representing 3D mesh information having a huge volume of information in a 3D scene can be efficiently encoded and decoded so that the 3D scene can be efficiently transmitted and stored. By transmitting and storing 3D mesh information of a node representing encoded 3D mesh information, through an independent stream separate from 3D scene description information, the entire 3D scene cannot be affected even though encoded 3D mesh information has a huge volume.
摘要翻译：提供了一种用于处理三维（3D）场景中的节点的方法及其装置。该方法包括以下步骤：识别具有3D网格信息的3D网格节点，所述3D网格信息表示通过从包含在要处理的3D场景中的节点中的顶点构造面而形成的3D形状; 以及对所识别的3D网格节点进行编码或解码。此外，该方法包括通过与3D场景描述流分离的独立流来发送或存储编码的3D网格节点的3D网格信息的步骤。根据该方法，可以有效地编码和解码表示具有3D场景中的大量信息的3D网格信息的节点，从而可以有效地发送和存储3D场景。通过发送和存储表示编码的3D网格信息的节点的3D网格信息，通过与3D场景描述信息分离的独立流，即使编码的3D网格信息具有巨大的体积，也不会影响整个3D场景。

58. 发明授权

US09652656B2 Method and apparatus for generating organ image 有权
公开(公告)号：US09652656B2
公开(公告)日：2017-05-16
申请号：US13544859
申请日：2012-07-09
申请人： Yong-sun Kim , Jung-bae Kim , Young-kyoo Hwang , Won-chul Bang , Do-kyoon Kim
发明人： Yong-sun Kim , Jung-bae Kim , Young-kyoo Hwang , Won-chul Bang , Do-kyoon Kim
IPC分类号： G06K9/00 , G06T5/50
CPC分类号： G06K9/00 , G06T5/50 , G06T2207/10072 , G06T2207/30056
摘要： A method and apparatus for generating an organ image are provided. An organ image generating method involves: receiving image data of a medical image of a subject; extracting an image of an organ from the medical image; receiving image data of a generic image of the organ; and generating image data of an organ image of the subject from the generic image of the organ and the extracted image of the organ.

59. 发明授权

US08487926B2 Method and apparatus for generating 3D image using 2D photograph images 有权
公开(公告)号：US08487926B2
公开(公告)日：2013-07-16
申请号：US12078181
申请日：2008-03-27
申请人： Hee-sae Lee , Young-Ihn Kho , Jeong-hwan Ahn , Do-kyoon Kim
发明人： Hee-sae Lee , Young-Ihn Kho , Jeong-hwan Ahn , Do-kyoon Kim
IPC分类号： G06T15/00
CPC分类号： G06T3/4038 , G06T7/30 , G06T15/205
摘要： Provided is a method and apparatus for generating a 3D image including: generating a 2D panorama image showing the whole scene by combining a plurality of 2D images, each of which partially showing the scene; and generating a 3D image by folding the 2D panorama image on the basis of image information on the 2D panorama image.

60. 发明授权

US08218893B2 Image inpainting method and apparatus based on viewpoint change 有权
标题翻译：基于视点变化的图像修复方法和装置
公开(公告)号：US08218893B2
公开(公告)日：2012-07-10
申请号：US12216379
申请日：2008-07-02
申请人： Hwa-sup Lim , Jae-young Sim , Do-kyoon Kim , Kee-chang Lee
发明人： Hwa-sup Lim , Jae-young Sim , Do-kyoon Kim , Kee-chang Lee
IPC分类号： G06K9/40
CPC分类号： G06T15/205
摘要： Provided is a method and apparatus for inpainting a depth image and a color image seen from one viewpoint by using a depth image and a color image inpainted from another viewpoint. The method includes detecting an edge on the basis of a difference between depth values of pixels in a first image seen from a view viewpoint and inpainting depth values of pixels in an occlusion region that is shown in a second image seen from a second viewpoint but not shown in the first image, in a direction from pixels in a region having high depth values among regions forming the edge to pixels in a region having low depth values.
摘要翻译：提供了一种用于通过使用深度图像和从另一观点重新绘制的彩色图像来从一个视点观察深度图像和彩色图像的方法和装置。该方法包括基于从视点观察到的第一图像中的像素的深度值之间的差异来检测边缘，并且对从第二视点看到的第二图像中所示的遮挡区域中的像素的深度值进行修补在具有低深度区域的区域中形成边缘的区域中的具有高深度值的区域中的像素的方向显示在第一图像中。

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