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。

2. 发明申请

US20090190852A1 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：US20090190852A1
公开(公告)日：2009-07-30
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： G06K9/42
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。

3. 发明申请

US20090103782A1 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：US20090103782A1
公开(公告)日：2009-04-23
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
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。

4. 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。

5. 发明申请

US20090174710A1 Modeling method and apparatus 审中-公开
标题翻译：建模方法和装置
公开(公告)号：US20090174710A1
公开(公告)日：2009-07-09
申请号：US12216248
申请日：2008-07-01
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： G06T7/60 , G06K9/46
CPC分类号： G06K9/4638 , G06K9/00201 , G06T17/20
摘要： A modeling method and apparatus are provided, in which a vertex for each pixel of a depth image representing an object, the vertex having a 3-D position corresponding to the depth value of each pixel, is generated, grouping is performed on pixels which belong to a non-boundary of the object, among the pixels of the depth image, so that each pixel in the non-boundary of the object and adjacent pixels of the pixel are grouped into one group, and a polygonal mesh that is a set of at least one polygon is generated by connecting the vertices in consideration of the results of grouping.
摘要翻译：提供了一种建模方法和装置，其中生成表示对象的深度图像的每个像素的顶点，具有与每个像素的深度值对应的3-D位置的顶点，对属于的像素进行分组到所述对象的非边界，在所述深度图像的像素中，使得所述对象的非边界中的每个像素和所述像素的相邻像素被分组为一个组，并且所述多边形网格是一组考虑到分组的结果，通过连接顶点来生成至少一个多边形。

6. 发明申请

US20090161989A1 Method, medium, and apparatus representing adaptive information of 3D depth image 有权
标题翻译：表示3D深度图像的自适应信息的方法，介质和装置
公开(公告)号：US20090161989A1
公开(公告)日：2009-06-25
申请号：US12219444
申请日：2008-07-22
申请人： Jae-young Sim
发明人： Jae-young Sim
IPC分类号： G06K9/32
CPC分类号： H04N19/124 , H04N13/261 , H04N19/134 , H04N19/169 , H04N19/597
摘要： A method, medium, and apparatus processing depth information of a depth image. The apparatus adaptively presenting information on depth information includes a section determination unit determining which one of plural sections respective depth values for pixels of the 3D image fall within, with the plural sections being defined by a measured limit distance for the 3D image being parsed into the plural sections based on distance based depth resolution information, and an adaptive quantization unit to selectively quantize and represent each depth value based on a respective predefined quantization setting of the one section.
摘要翻译：深度图像的方法，介质和装置处理深度信息。自适应地呈现关于深度信息的信息的装置包括：区间确定单元，确定多个区域中的哪个区域，3D图像的像素的各个深度值落入其中，其中多个区段由被分析成3D图像的测量的限定距离定义基于基于距离的深度分辨率信息的多个部分，以及自适应量化单元，用于基于所述一个部分的各自的预定义量化设置选择性地量化和表示每个深度值。

7. 发明授权

US08243095B2 Rendering apparatus and method 有权
标题翻译：渲染装置和方法
公开(公告)号：US08243095B2
公开(公告)日：2012-08-14
申请号：US11889625
申请日：2007-08-15
申请人： Jae-young Sim , Seok-yoon Jung
发明人： Jae-young Sim , Seok-yoon Jung
IPC分类号： G09G5/00
CPC分类号： G06T15/205
摘要： Provided is a rendering apparatus and method. After a rendering image is generated by forming a splat for each of points generated by projecting a model composed of a plurality of points, then a plurality of predetermined regions which extend over a boundary of the generated rendering image are selected for each splat forming the boundary of the rendering image, and a pixel value of each pixel included in each of the selected regions is corrected based on pixel values of the pixel and its surrounding pixels, thereby correcting the boundary of the rendering image to make the boundary appear to be more natural and thus improving the display quality of the rendering image.
摘要翻译：提供了一种渲染装置和方法。在通过对通过投影由多个点组成的模型进行投影而生成的每个点形成画面来生成渲染图像之后，对于形成边界的每个拼接选择在生成的渲染图像的边界上延伸的多个预定区域并且基于像素及其周围像素的像素值来校正每个所选择的区域中包括的每个像素的像素值，从而校正渲染图像的边界，使边界看起来更自然从而提高渲染图像的显示质量。

8. 发明申请

US20080180454A1 Rendering apparatus and method 有权
标题翻译：渲染装置和方法
公开(公告)号：US20080180454A1
公开(公告)日：2008-07-31
申请号：US11889625
申请日：2007-08-15
申请人： Jae-young Sim , Seok-Yoon Jung
发明人： Jae-young Sim , Seok-Yoon Jung
IPC分类号： G09G5/00
CPC分类号： G06T15/205
摘要： Provided is a rendering apparatus and method. After a rendering image is generated by forming a splat for each of points generated by projecting a model composed of a plurality of points, then a plurality of predetermined regions which extend over a boundary of the generated rendering image are selected for each splat forming the boundary of the rendering image, and a pixel value of each pixel included in each of the selected regions is corrected based on pixel values of the pixel and its surrounding pixels, thereby correcting the boundary of the rendering image to make the boundary appear to be more natural and thus improving the display quality of the rendering image.
摘要翻译：提供了一种渲染装置和方法。在通过对通过投影由多个点组成的模型进行投影产生的每个点形成拼接来生成再现图像之后，对于形成边界的每个拼接选择在生成的渲染图像的边界上延伸的多个预定区域并且基于像素及其周围像素的像素值来校正每个所选择的区域中包括的每个像素的像素值，从而校正渲染图像的边界，使边界看起来更自然从而提高渲染图像的显示质量。

9. 发明授权

US08620099B2 Method, medium, and apparatus representing adaptive information of 3D depth image 有权
公开(公告)号：US08620099B2
公开(公告)日：2013-12-31
申请号：US12219444
申请日：2008-07-22
申请人： Jae-young Sim
发明人： Jae-young Sim
IPC分类号： G06K9/00
CPC分类号： H04N19/124 , H04N13/261 , H04N19/134 , H04N19/169 , H04N19/597
摘要： A method, medium, and apparatus processing depth information of a depth image. The apparatus adaptively presenting information on depth information includes a section determination unit determining which one of plural sections respective depth values for pixels of the 3D image fall within, with the plural sections being defined by a measured limit distance for the 3D image being parsed into the plural sections based on distance based depth resolution information, and an adaptive quantization unit to selectively quantize and represent each depth value based on a respective predefined quantization setting of the one section.

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