公开(公告)号：US20130336577A1

公开(公告)日：2013-12-19

申请号：US13949372

申请日：2013-07-24

Applicant: Cyberlink Corp.

Inventor： Pei-Ying Lu ,  Chia-Chen Kuo ,  Chih-Yu Cheng

IPC: G06K9/00

CPC classification number: G06K9/00 ,  G06T7/194 ,  G06T7/215 ,  G06T7/579 ,  G06T2207/10024 ,  H04N13/15 ,  H04N13/261 ,  H04N13/264 ,  H04N2013/0085

Abstract: In one embodiment, a two-dimensional to stereoscopic conversion method, comprising: estimating a local motion region in a first image relative to one or more second images, the first and the one or more second images comprising two-dimensional images; generating a color model based on the local motion region; calculating a similarity value for each of at least one image pixel selected from the first image based on the color model; and assigning a depth value for each of the at least one image pixel selected from the first image based on the calculated similarity value to generate a stereoscopic image, the method performed by one or more processors.

Abstract translation: 在一个实施例中，一种二维立体转换方法，包括：估计第一图像中相对于一个或多个第二图像的局部运动区域，所述第一图像和所述一个或多个第二图像包括二维图像; 基于局部运动区域生成颜色模型; 基于所述颜色模型计算从所述第一图像中选择的至少一个图像像素中的每一个的相似度值; 以及基于所计算的相似度值为从所述第一图像中选择的所述至少一个图像像素中的每一个分配深度值以生成立体图像，所述方法由一个或多个处理器执行。

公开(公告)号：US09633460B2

公开(公告)日：2017-04-25

申请号：US14138179

申请日：2013-12-23

Applicant: Cyberlink Corp.

Inventor： Hao-Ping Hung ,  Pei-Ying Lu

IPC: G06K9/46 ,  G06T11/60 ,  G06T5/00

CPC classification number: G06T11/60 ,  G06T5/002 ,  G06T5/003 ,  G06T2207/20221

Abstract: A method implemented in an image editing device comprises determining a source region in a source image and determining a target region in a target image. At least one image characteristic of each of the source region and a region outside the target region is analyzed. The content in the source region is adjusted according to the at least one image characteristic of the source region and the at least one image characteristic of the region outside the target region. The adjusted content from the source region is inserted into the target region.

公开(公告)号：US08995755B2

公开(公告)日：2015-03-31

申请号：US13949372

申请日：2013-07-24

Applicant: Cyberlink Corp.

Inventor： Pei-Ying Lu ,  Chia-Chen Kuo ,  Chih-Yu Cheng

IPC: G06K9/00 ,  G06T7/00 ,  G06T7/20 ,  H04N13/00 ,  H04N13/02

CPC classification number: G06K9/00 ,  G06T7/194 ,  G06T7/215 ,  G06T7/579 ,  G06T2207/10024 ,  H04N13/15 ,  H04N13/261 ,  H04N13/264 ,  H04N2013/0085

Abstract: In one embodiment, a two-dimensional to stereoscopic conversion method, comprising: estimating a local motion region in a first image relative to one or more second images, the first and the one or more second images comprising two-dimensional images; generating a color model based on the local motion region; calculating a similarity value for each of at least one image pixel selected from the first image based on the color model; and assigning a depth value for each of the at least one image pixel selected from the first image based on the calculated similarity value to generate a stereoscopic image, the method performed by one or more processors.

Abstract translation: 在一个实施例中，一种二维立体转换方法，包括：估计第一图像中相对于一个或多个第二图像的局部运动区域，所述第一图像和所述一个或多个第二图像包括二维图像; 基于局部运动区域生成颜色模型; 基于所述颜色模型计算从所述第一图像中选择的至少一个图像像素中的每一个的相似度值; 以及基于所计算的相似度值为从所述第一图像中选择的所述至少一个图像像素中的每一个分配深度值以生成立体图像，所述方法由一个或多个处理器执行。

公开(公告)号：US20140270535A1

公开(公告)日：2014-09-18

申请号：US14138179

申请日：2013-12-23

Applicant: CYBERLINK CORP.

Inventor： Hao-Ping Hung ,  Pei-Ying Lu

IPC: G06K9/03

CPC classification number: G06T11/60 ,  G06T5/002 ,  G06T5/003 ,  G06T2207/20221

Abstract: A method implemented in an image editing device comprises determining a source region in a source image and determining a target region in a target image. At least one image characteristic of each of the source region and a region outside the target region is analyzed. The content in the source region is adjusted according to the at least one image characteristic of the source region and the at least one image characteristic of the region outside the target region. The adjusted content from the source region is inserted into the target region.

Abstract translation: 在图像编辑装置中实现的方法包括：确定源图像中的源区域并确定目标图像中的目标区域。 分析源区域和目标区域之外的区域中的每一个的至少一个图像特征。 根据源区域的至少一个图像特性和目标区域外的区域的至少一个图像特性来调整源区域中的内容。 来自源区域的调整内容被插入到目标区域中。