公开(公告)号：US11010967B2

公开(公告)日：2021-05-18

申请号：US16352064

申请日：2019-03-13

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jae-yun Jeong ,  Alexander Limonov

IPC: G06T15/04 ,  G06T15/20 ,  G06K9/00 ,  G06T7/73 ,  G06T7/55 ,  G06T17/10

Abstract: A three dimensional (3D) content generating apparatus includes an inputter configured to receive a plurality of images of an object captured from different locations; a detector configured to identify the object and detect a predetermined feature point of the object from each of the plurality of images; a map former configured to extract 3D location information of the detected feature point, and configured to form at least one depth map with respect to a surface of the object based on the extracted 3D location information of the feature point; and a content generator configured to generate a 3D content of the object using the at least one depth map and the plurality of images.

公开(公告)号：US10269175B2

公开(公告)日：2019-04-23

申请号：US15185896

申请日：2016-06-17

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jae-yun Jeong ,  Alexander Limonov

IPC: G06T17/10 ,  G06T7/55 ,  G06K9/00 ,  G06T15/20 ,  G06T7/73 ,  G06T15/04

Abstract: A three dimensional (3D) content generating apparatus includes an inputter configured to receive a plurality of images of an object captured from different locations; a detector configured to identify the object and detect a predetermined feature point of the object from each of the plurality of images; a map former configured to extract 3D location information of the detected feature point, and configured to form at least one depth map with respect to a surface of the object based on the extracted 3D location information of the feature point; and a content generator configured to generate a 3D content of the object using the at least one depth map and the plurality of images.

公开(公告)号：US09195881B2

公开(公告)日：2015-11-24

申请号：US14024113

申请日：2013-09-11

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Do-wan Kim ,  Alexander Limonov ,  Jin-sung Lee ,  Kil-soo Jung

IPC: G06K9/42 ,  G06K9/00 ,  G06T3/00

CPC classification number: G06K9/00281 ,  G06T3/0006 ,  G06T3/0093

Abstract: An image transformation apparatus includes a detection unit which is configured to detect, from each of a user image and a reference image, feature points of a face and angle information of the face, a feature points adjusting unit which is configured to adjust the feature points of the user image or the reference image by using the detected angle information, a face analysis unit which is configured to compare facial features contained in the user image and the reference image by using the adjusted feature points, and an image transformation unit which is configured to transform the user image by using a result of the comparison of the facial features from the face analysis unit.

Abstract translation: 一种图像变换装置，包括检测单元，其被配置为从用户图像和参考图像中的每一个检测面部的特征点和脸部的角度信息，特征点调整单元，被配置为调整特征点 通过使用所检测的角度信息来显示所述用户图像或所述参考图像;面部分析单元，被配置为通过使用所调整的特征点来比较包含在所述用户图像中的面部特征和所述参考图像;以及图像变换单元， 通过使用来自面部分析单元的面部特征的比较的结果来变换用户图像。

公开(公告)号：US20190213786A1

公开(公告)日：2019-07-11

申请号：US16352064

申请日：2019-03-13

Applicant: Samsung Electronics Co., Ltd.

Inventor： Jae-yun Jeong ,  Alexander Limonov

IPC: G06T17/10 ,  G06T7/55 ,  G06T7/73 ,  G06K9/00 ,  G06T15/20 ,  G06T15/04

CPC classification number: G06T17/10 ,  G06K9/00208 ,  G06K9/00268 ,  G06T7/55 ,  G06T7/74 ,  G06T15/04 ,  G06T15/205 ,  G06T2207/30201 ,  G06T2207/30244

Abstract: A three dimensional (3D) content generating apparatus includes an inputter configured to receive a plurality of images of an object captured from different locations; a detector configured to identify the object and detect a predetermined feature point of the object from each of the plurality of images; a map former configured to extract 3D location information of the detected feature point, and configured to form at least one depth map with respect to a surface of the object based on the extracted 3D location information of the feature point; and a content generator configured to generate a 3D content of the object using the at least one depth map and the plurality of images.

公开(公告)号：US08817020B2

公开(公告)日：2014-08-26

申请号：US14059962

申请日：2013-10-22

Applicant: Samsung Electronics Co., Ltd.

Inventor： Alexander Limonov ,  Jin-sung Lee ,  Jong-sul Min

IPC: G06T15/00 ,  G06T7/00

CPC classification number: G06T7/0051 ,  G06T7/50 ,  G06T15/00 ,  H04N13/128 ,  H04N13/183 ,  H04N21/4882 ,  H04N21/816 ,  H04N2013/0081 ,  H04N2013/0092

Abstract: An image processing apparatus and a method of processing an image are provided. The image processing apparatus includes a depth estimation unit for estimating a depth of an input three-dimensional (3D) image; a text area detection unit for detecting a text area included in the 3D image; a mask generation unit for generating a text mask for the text area; and a depth correction unit for correcting a depth of the text area based on the estimated depth of the input 3D image and the text mask.

Abstract translation: 提供了图像处理装置和图像处理方法。 图像处理装置包括用于估计输入三维（3D）图像的深度的深度估计单元; 文本区域检测单元，用于检测3D图像中包括的文本区域; 用于生成文本区域的文本掩码的掩码生成单元; 以及深度校正单元，用于基于所输入的3D图像和文本掩模的估计深度来校正文本区域的深度。