-
公开(公告)号：US10726612B2
公开(公告)日：2020-07-28
申请号：US16104431
申请日：2018-08-17
Inventor： Byung Ok Han , Jae Hwan Kim , Ho Won Kim , Ji Hyung Lee , Yu Gu Jung , Chang Joon Park , Gil Haeng Lee
Abstract: Provided is a method of reconstructing a three-dimensional (3D) model of an object. The method includes sequentially performing, by a camera module, first and second object scanning processes of scanning the same object, reconstructing, by a processor module, a 3D object model, based on a first object image obtained through the first object scanning process, performing pose learning on an object to generate learning data, based on data obtained through a process of reconstructing the 3D object model based on the first object image, and reconstructing, by the processor module, a final 3D object model, based on a second object image obtained through the second object scanning process and the learning data.
-
2.发明申请公开(公告)号：US20190164346A1
公开(公告)日：2019-05-30
申请号：US15888936
申请日：2018-02-05
Inventor： Ho Won Kim , Byung Ok Han , Yu Gu Jung , Jae Hwan Kim , Ji Hyung Lee , Chang Joon Park , Gil Haeng Lee
CPC classification number: G06T19/006 , G06F3/011 , G06T15/005 , G06T19/20
Abstract: The present invention relates to a method and apparatus for providing a realistic 2D/3D AR experience service based on a video. Particularly, the present invention provides a method of providing a realistic AR service with high quality based on AR by using a 2D video image and 3D information in association thereto at the same time, filming a cybernaut and AR content by using two sensors having viewpoints different from each other, and arranging 2D/3D content being an object to be matched within the AR content and which has a 3D position different to a position of the cybernaut in association with a dynamic 3D position of the cybernaut and with a dynamic viewpoint of a service sensor.
-
3.发明授权公开(公告)号：US10417829B2
公开(公告)日：2019-09-17
申请号：US15888936
申请日：2018-02-05
Inventor： Ho Won Kim , Byung Ok Han , Yu Gu Jung , Jae Hwan Kim , Ji Hyung Lee , Chang Joon Park , Gil Haeng Lee
Abstract: The present invention relates to a method and apparatus for providing a realistic 2D/3D AR experience service based on a video. Particularly, the present invention provides a method of providing a realistic AR service with high quality based on AR by using a 2D video image and 3D information in association thereto at the same time, filming a cybernaut and AR content by using two sensors having viewpoints different from each other, and arranging 2D/3D content being an object to be matched within the AR content and which has a 3D position different to a position of the cybernaut in association with a dynamic 3D position of the cybernaut and with a dynamic viewpoint of a service sensor.
-
公开(公告)号：US09367944B2
公开(公告)日：2016-06-14
申请号：US13959260
申请日：2013-08-05
Inventor： Jae Hwan Kim , Il Kwon Jeong
Abstract: Provided is a tree model generating method according to an embodiment of the present invention. The tree model generating method includes separating and extracting a skeleton of a tree from an image including the tree to generate a matte image, applying a graph representation scheme of a two-dimensional (2D) object to the matte image to generate an object skeleton graph, generating a depth information value in accordance with a predetermined rule and allocating the generated depth information value to each node on the object skeleton graph to generate a three-dimensional (3D) primary tree model, adding branches to the primary tree model based on a branch library constructed in advance and the predetermined rule to generate a secondary tree model, and performing self-growth representation with respect to the secondary tree model based on a distance between each node on the object skeleton graph to generate a tertiary tree model.
Abstract translation: 提供了根据本发明的实施例的树模型生成方法。 树模型生成方法包括从包括树的图像分离和提取树的骨架以生成无光泽图像，将二维（2D）对象的图表示方案应用于无光图像以生成对象骨架图 根据预定规则生成深度信息值，并将所生成的深度信息值分配给对象骨架图上的每个节点，以生成三维（3D）主树模型，基于主树模型将分支添加到主树模型 提前构建的分支库和预定规则以生成辅助树模型，并且基于对象骨架图上的每个节点之间的距离来执行关于次树模型的自生长表示以生成第三树模型。
-
-
-
Search Results
4
records
(took 0.013 seconds)
