-
公开(公告)号：US20200151963A1
公开(公告)日：2020-05-14
申请号：US16557726
申请日：2019-08-30
Inventor： Seung-Wook LEE , Tae-Joon KIM , Seung-Uk YOON , Seong-Jae LIM , Bon-Woo HWANG , Jin-Sung CHOI
Abstract: Disclosed herein are an apparatus and method for generating a training data set for machine learning. The method for generating a training data set, performed by the apparatus for generating the training data set for machine learning, includes generating a 3D model for a deformed 3D character based on 3D data pertaining to the 3D character, generating a 2D image corresponding to the 3D model, and generating the training data set for machine learning, through which the 3D character is generated from the 2D image, using the 2D image and the 3D model.
-
公开(公告)号：US20170126674A1
公开(公告)日：2017-05-04
申请号：US15331477
申请日：2016-10-21
Inventor： Seung-Wook LEE
IPC: H04L29/06 , G05B19/042
CPC classification number: H04L63/0869 , B33Y10/00 , B33Y50/02 , G05B2219/49023 , H04L63/0807 , H04W12/06
Abstract: Disclosed herein are a three-way authentication apparatus and method in a cloud environment. The three-way authentication method in a cloud environment includes performing, by a control device and a service device, mutual authentication through an IF-1 interface, performing, by the control device and a function server, mutual authentication through an IF-2 interface, requesting, by the control device, the function server to issue an authentication token for authentication between the service device and the function server, and delivering an authentication token issued by the function server to the service device, and performing, by the service device, mutual authentication with the function server using the delivered authentication token through an IF-3 interface.
-
公开(公告)号：US20210158606A1
公开(公告)日：2021-05-27
申请号：US16950457
申请日：2020-11-17
Inventor： Seung-Wook LEE , Ki-Nam KIM , Tae-Joon KIM , Seung-Uk YOON , Seong-Jae LIM , Bon-Woo HWANG , Chang-Joon PARK
Abstract: Disclosed herein are an apparatus and method for generating a 3D model. The apparatus for generating a 3D model includes one or more processors, and an execution memory for storing at least one program that is executed by the one or more processors, wherein the at least one program is configured to receive two-dimensional (2D) original image layers for respective viewpoints, and generate pieces of 2D original image information for respective objects by performing original image alignment on the 2D original image layers for respective viewpoints for each predefined object type, generate 3D model layers for respective objects from the pieces of 2D original image information for respective objects using multiple learning models corresponding to the predefined object types, and generate a 3D model by synthesizing the 3D model layers for respective objects.
-
公开(公告)号：US20180107531A1
公开(公告)日：2018-04-19
申请号：US15725935
申请日：2017-10-05
Inventor： Seung-Wook LEE , Chang-Joon PARK , Jin-Sung CHOI
CPC classification number: G06F9/546 , B29C64/393 , B33Y50/02 , G06F16/176 , G06F21/33 , G06F21/629 , H04L63/0807 , H04L63/102
Abstract: Disclosed herein are a service server, a user terminal, and a method of 3D collaborative printing providing a 3D collaborative printing service. A method of 3D collaborative printing performed by a 3D collaborative printing system includes generating, by a user terminal, control information to store the control information in a service server; generating, by the service server, a secure token to transmit the secure token to the user terminal; transmitting, by the user terminal, the secure token to one or more 3D printer; receiving, by the one or more 3D printer, the control information corresponding to the secure token from the service server using the secure token; and performing, by the one or more 3D printer, an operation corresponding to the control information.
-
5.发明申请DEVICE AND METHOD FOR SUPPORTING 3D OBJECT PRINTING AND APPARATUS FOR PROVIDING 3D OBJECT PRINTING SERVICE 审中-公开用于支持3D对象打印的设备和方法以及用于提供3D对象打印服务的设备公开(公告)号：US20150032241A1
公开(公告)日：2015-01-29
申请号：US14325816
申请日：2014-07-08
Inventor： Seung-Wook LEE , In-Su JANG , Jin-Sung CHOI , Bon-Ki KOO
IPC: B29C67/00
CPC classification number: B29C67/0088 , B29C64/386 , B33Y50/02
Abstract: Disclosed herein is a device and method for supporting 3D object printing and an apparatus for providing a 3D object printing service. A proposed device for supporting 3D object printing includes an information collection unit for collecting preference information of a user and performance information of a 3D printer. A download unit downloads a 3D model that is an object to be printed and model information defined in the 3D model in response to a printable selection signal. A model information creation unit creates new model information based on the 3D model and the model information defined in the 3D model. A print control command generation unit generates a print control command based on the preference information of the user and the performance information of the 3D printer, output from the information collection unit, and the new model information, output from the model information creation unit.
Abstract translation: 本文公开了一种用于支持3D对象打印的装置和方法以及用于提供3D对象打印服务的装置。 用于支持3D对象打印的所提出的装置包括用于收集用户的偏好信息和3D打印机的性能信息的信息收集单元。 下载单元响应于可打印的选择信号下载作为要打印的对象的3D模型和在3D模型中定义的模型信息。 模型信息创建单元基于3D模型和在3D模型中定义的模型信息创建新的模型信息。 打印控制命令生成单元基于从模型信息创建单元输出的用户的偏好信息和从信息收集单元输出的3D打印机的性能信息和新的模型信息，生成打印控制命令。
-
Patent Agency Ranking
公开(公告)号：US20210136280A1
公开(公告)日：2021-05-06
申请号：US17085077
申请日：2020-10-30
Inventor： Seong-Jae LIM , Ki-Nam KIM , Tae-Joon KIM , Seung-Uk YOON , Seung-Wook LEE , Bon-Woo HWANG
IPC: H04N5/232 , H04N13/275
Abstract: Disclosed herein are an apparatus and method for guiding multi-view capture. The apparatus for guiding multi-view capture includes one or more processors and an execution memory for storing at least one program that is executed by the one or more processors, wherein the at least one program is configured to receive a single-view two-dimensional (2D) image obtained by capturing an image of an object of interest through a camera, generate an orthographic projection image and a perspective projection image for the object of interest from the single-view 2D image using an image conversion parameter that is previously learned from multi-view 2D images for the object of interest, generate a 3D silhouette model for the object of interest using the orthographic projection image and the perspective projection image, and output the 3D silhouette model and a guidance interface for the 3D silhouette model.
-
公开(公告)号：US20200273247A1
公开(公告)日：2020-08-27
申请号：US16752260
申请日：2020-01-24
Inventor： Seong-Jae LIM , Tae-Joon KIM , Seung-Uk YOON , Seung-Wook LEE , Bon-Woo HWANG , Jin-Sung CHOI
Abstract: Disclosed herein are a learning-based three-dimensional (3D) model creation apparatus and method. A method for operating a learning-based 3D model creation apparatus includes generating multi-view feature images using supervised learning, creating a three-dimensional (3D) mesh model using a point cloud corresponding to the multi-view feature images and a feature image representing internal shape information, generating a texture map by projecting the 3D mesh model into three viewpoint images that are input, and creating a 3D model using the texture map.
-
8.发明申请METHOD FOR CONFIGURING INFORMATION RELATED TO A 3D PRINTER AND METHOD AND APPARATUS FOR RECOMMENDING A 3D PRINTER 审中-公开用于配置与3D打印机相关的信息的方法和用于推荐3D打印机的方法和装置公开(公告)号：US20150277811A1
公开(公告)日：2015-10-01
申请号：US14670968
申请日：2015-03-27
Inventor： Seung-Wook LEE , Kap-Kee KIM , Jin-Sung CHOI
IPC: G06F3/12
CPC classification number: B33Y50/02 , B29C64/386
Abstract: Exemplary embodiments of the present invention provide optimized 3D printings to a user by inserting metadata (i.e., a current model should be printed with a strong heat resistance material) to a 3D object for 3D printing and combining preference of a default printing material which a user desires (i.e., since glass is fragile, it does not like to print with glass) based thereon and printer performance of the user's (i.e., the printer which can print glass and plastic).
Abstract translation: 本发明的示例性实施例通过将用于3D打印的元数据（即，当前模型应当用强耐热材料印刷）提供给3D对象来提供优化的3D打印，并且组合用户的默认打印材料的偏好 （即，由于玻璃易碎，不喜欢用玻璃打印），并且用户（即，可以印刷玻璃和塑料的打印机）的打印机性能。
-
公开(公告)号：US20130195330A1
公开(公告)日：2013-08-01
申请号：US13753378
申请日：2013-01-29
Inventor： Ho-Won KIM , Seung-Wook LEE , Ji-Hyung LEE , Bon-Ki KOO
IPC: G06K9/00
CPC classification number: G06K9/00362 , G06K9/00201 , G06T2200/04 , G06T2207/20044 , G06T2207/30196
Abstract: Disclosed herein is an apparatus and method for estimating the joint structure of a human body. The apparatus includes a multi-view image acquisition unit for receiving multi-view images acquired by capturing a human body. A human body foreground separation unit extracts a foreground region corresponding to the human body from the acquired multi-view images. A human body shape restoration unit restores voxels indicating geometric space occupation information of the human body using the foreground region corresponding to the human body, thus generating voxel-based three-dimensional (3D) shape information of the human body. A skeleton information extraction unit generates 3D skeleton information from the generated voxel-based 3D shape information of the human body. A skeletal structure estimation unit estimates positions of respective joints from a skeletal structure of the human body using both the generated 3D skeleton information and anthropometric information.
Abstract translation: 这里公开了一种用于估计人体关节结构的装置和方法。 该装置包括：多视点图像获取单元，用于接收通过捕获人体获取的多视点图像。 人体前景分离部从所获取的多视图图像中提取与人体对应的前景区域。 人体形状修复单元使用与人体对应的前景区域恢复表示人体的几何空间占用信息的体素，从而生成人体的基于体素的三维（3D）形状信息。 骨架信息提取单元根据生成的基于体素的基于体素的3D形状信息生成3D骨架信息。 骨骼结构估计单元使用生成的3D骨架信息和人体测量信息来估计来自人体的骨骼结构的各个关节的位置。
-
公开(公告)号：US20220101604A1
公开(公告)日：2022-03-31
申请号：US17550606
申请日：2021-12-14
Inventor： Seong-Jae LIM , Tae-Joon KIM , Seung-Uk YOON , Seung-Wook LEE , Bon-Woo HWANG , Jin-Sung CHOI
Abstract: Disclosed herein are a learning-based three-dimensional (3D) model creation apparatus and method. A method for operating a learning-based 3D model creation apparatus includes generating multi-view feature images using supervised learning, creating a three-dimensional (3D) mesh model using a point cloud corresponding to the multi-view feature images and a feature image representing internal shape information, generating a texture map by projecting the 3D mesh model into three viewpoint images that are input, and creating a 3D model using the texture map.
-
-
-
-
-
-
-
-
-
Search Results
12
records
(took 0.025 seconds)
