公开(公告)号：US20240211754A1

公开(公告)日：2024-06-27

申请号：US18447836

申请日：2023-08-10

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： IL KYU PARK ,  Bonki KOO

IPC: G06N3/08

CPC classification number: G06N3/08

Abstract: An embodiment of the present disclosure discloses a method of operating a computing device for mapping data from different domains to a common joint embedding space, and the method of operating a computing device includes training a mapping neural network constituting a joint embedding space using an input dataset, generating a prediction matrix of an input dataset using the mapping neural network, and generating a merging dictionary merging classes from the prediction matrix to correct the input dataset.

公开(公告)号：US20220358720A1

公开(公告)日：2022-11-10

申请号：US17545476

申请日：2021-12-08

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Jae Hean KIM ,  Bonki KOO

IPC: G06T17/20 ,  G06T7/90 ,  G06T15/04 ,  G06T19/20

Abstract: A method for generating three-dimensional (3D) content for a performance of a performer in an apparatus for generating 3D content is provided. The apparatus for generating 3D content obtains a 3D appearance model and texture information of the performer using the images of the performer located in the space, sets a plurality of nodes in the 3D appearance model of the performer, generates a 3D elastic model of the performer using the texture information, obtains a plurality of first images of the performance scene of the performer photographed by a plurality of first cameras installed in a performance hall, renders a plurality of virtual images obtained by photographing a 3D appearance model according to position change of each node in a 3D elastic model of the performer through a plurality of first virtual cameras having the same intrinsic and extrinsic parameters as the plurality of first cameras, using the texture information, determines an optimal position of each node by using color differences between the plurality of first images and a plurality of first rendered with respect to the plurality of virtual images obtained by the plurality of first virtual cameras, and generates a mesh model describing the performance scene by applying 3D elastic model parameter values corresponding to the optimal position of each node to the 3D elastic model.

公开(公告)号：US20220335675A1

公开(公告)日：2022-10-20

申请号：US17525829

申请日：2021-11-12

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Jin Sung CHOI ,  Bonki KOO ,  Yong Sun KIM ,  Jae Hean KIM ,  Byungkuk SEO

IPC: G06T15/00 ,  G06T15/20 ,  G06T7/194 ,  G06T7/11

Abstract: The present disclosure relates to a mixed phenomena expressing method for expressing physical phenomena in a mixed reality and a mixed reality apparatus for performing the method. To be more specific, the physical phenomena expressing method configures a scene which may enhance a context or a realism to have the same level as the face-to-face situation using a scene configuration of the input image collected from the sensor to provide a service of a mixed reality and a physics/physical property analysis of a target object included in the input image.

公开(公告)号：US20240257468A1

公开(公告)日：2024-08-01

申请号：US18537544

申请日：2023-12-12

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Kap Kee KIM ,  Bonki KOO

IPC: G06T17/30 ,  G06T15/20

CPC classification number: G06T17/30 ,  G06T15/20

Abstract: Disclosed is an operation method of an electronic device, the method including: identifying a first quaternion value corresponding to rotation of a first object and a second quaternion value corresponding to rotation of a second object; identifying, on the basis of the first quaternion value, a first axis around which the first object rotates; identifying, on the basis of the second quaternion value, a second axis around which the second object rotates; identifying a first rotation angle related to rotation of the first object around the first axis, and a second rotation angle related to rotation of the second object around the second axis; identifying a first angle formed by the first and second axes; identifying a second angle corresponding to a difference between the first and second rotation angles; and determining a quaternion distance between the first and second objects on the basis of the first and second angles.

公开(公告)号：US20150078621A1

公开(公告)日：2015-03-19

申请号：US14449036

申请日：2014-07-31

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Yoonseok CHOI ,  Soonchul JUNG ,  Jinsung CHOI ,  Bonki KOO

IPC: G06T7/20 ,  G09G5/14

CPC classification number: G09G5/14 ,  A63F13/213 ,  A63F13/65 ,  G06F3/00 ,  G06F3/011 ,  G06F3/017 ,  G06F3/0304 ,  G06T7/246 ,  G06T2207/10016 ,  G06T2207/30196 ,  G06T2207/30204 ,  H04N21/2187

Abstract: A method and apparatus for providing content experience service are disclosed. The apparatus includes a camera device tracking unit, a user behavior tracking unit, a real image acquisition unit, a motion information processing unit, a virtual space control unit, and a virtual multi-image generation unit. The camera device tracking unit collects camera motion information. The user behavior tracking unit collects user motion information. The real image acquisition unit photographs a space including the user, and separates a real image into a foreground and a background using a background key table. The motion information processing unit corrects the camera motion information and the user motion information. The virtual space control unit generates virtual space control information and virtual space information. The virtual multi-image generation unit generates a virtual multi-image, and provides the content experience service based on the generated virtual multi-image.

Abstract translation: 公开了一种用于提供内容体验服务的方法和装置。 该装置包括相机设备跟踪单元，用户行为跟踪单元，实际图像获取单元，运动信息处理单元，虚拟空间控制单元和虚拟多图像生成单元。 相机设备跟踪单元收集相机运动信息。 用户行为跟踪单元收集用户运动信息。 真实图像获取单元拍摄包括用户的空间，并且使用背景键表将真实图像分离成前景和背景。 运动信息处理单元校正摄像机运动信息和用户运动信息。 虚拟空间控制单元生成虚拟空间控制信息和虚拟空间信息。 虚拟多图像生成单元生成虚拟多图像，并且基于生成的虚拟多图像提供内容体验服务。