-
公开(公告)号：US20240290007A1
公开(公告)日：2024-08-29
申请号：US18466143
申请日：2023-09-13
Inventor： Donghoon SAGONG , Haechan LEE , Sunghyun CHO , Seung-Hwan BAEK , Nahyup KANG , Jiyeon KIM
CPC classification number: G06T11/001 , G06T7/90 , G06T15/205 , G06T17/10 , G06T2207/10012 , G06T2207/10024 , G06T2207/20084
Abstract: A processor-implemented method includes: extracting pyramid level color feature maps from two or more images; extracting pyramid level density feature maps based on a cost volume generated based on the color feature maps; generating neural scene representation (NSR) cube information representing a three-dimensional (3D) space based on the color feature maps and the density feature maps; and generating a two-dimensional (2D) scene of a field of view (FOV) different from a FOV of the two or more images based on the NSR cube information.
-
公开(公告)号：US20240147052A1
公开(公告)日：2024-05-02
申请号：US18307213
申请日：2023-04-26
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Heesae LEE , Jiyeon KIM
CPC classification number: H04N23/631 , H04N23/633 , H04N23/64 , H04N23/71 , H04N23/72 , H04N23/80
Abstract: An apparatus including a processor configured to execute a plurality of instructions and a memory storing the plurality of instructions, wherein execution of the plurality of instructions configures the processor to be configured to encode a dynamic event including a plurality of first images received from a camera, receive a selection of a target camera position and a target light quantity in response to a user input from among the plurality of first images, and generate a target image by performing decoding based on the target camera position and the target light quantity.
-
公开(公告)号：US20180108142A1
公开(公告)日：2018-04-19
申请号：US15677213
申请日：2017-08-15
Applicant: Samsung Electronics Co., Ltd.
Inventor： Minsu AHN , Jiyeon KIM , Hyong Euk LEE , Young Hun SUNG
CPC classification number: G06T7/593 , G06K9/4604 , G06K9/4671 , G06T7/586 , G06T7/97 , G06T2207/10012 , G06T2207/10024 , H04N13/128 , H04N2013/0081
Abstract: An image processing apparatus includes a processor configured to calculate a curvature value of a first point in stereo images based on a disparity value corresponding to the first point, and refine the disparity value based on the curvature value.
-
公开(公告)号：US20170161413A1
公开(公告)日：2017-06-08
申请号：US15355325
申请日：2016-11-18
Applicant: Samsung Electronics Co., Ltd.
Inventor： Donghoon SAGONG , Nahyup KANG , Jiyeon KIM , Hyong Euk LEE , Hwiryong JUNG
CPC classification number: G06F17/5009 , G06F17/11 , G06F17/5018 , G06F2217/16
Abstract: A fluid particle modeling method includes determining bubble cells based on locations of fluid particles, defining a bubble based on the bubble cells, calculating a pressure of the bubble based on a change in a volume of the bubble, and updating the locations of the fluid particles based on the pressure of the bubble.
-
5.发明申请METHOD AND APPARATUS FOR MODELING BASED ON PARTICLES FOR EFFICIENT CONSTRAINTS PROCESSING 审中-公开基于有效约束处理颗粒的建模方法与装置公开(公告)号：US20170024498A1
公开(公告)日：2017-01-26
申请号：US15187135
申请日：2016-06-20
Applicant: Samsung Electronics Co., Ltd.
Inventor： Nahyup KANG , Jiyeon KIM , Donghoon SAGONG , Hyong Euk LEE , Hwiryong JUNG
Abstract: A modeling method based on particles, the method including generating coarse particles by down-sampling target particles corresponding to at least a portion of a target object, calculating a correcting value enabling the coarse particles to satisfy constraints of the target object based on physical attributes of the target particles, applying the correcting value to the target particles, and redefining the target particles in response to the target particles to which the correcting value is applied satisfying the constraints.
Abstract translation: 一种基于粒子的建模方法，该方法包括：通过对与目标对象的至少一部分相对应的目标粒子进行下采样来生成粗粒子;计算使得粗粒子能够基于物理属性的物理属性来满足目标对象的约束的校正值 目标颗粒，将校正值应用于目标颗粒，并且响应于满足约束条件的施加了校正值的目标颗粒重新定义目标颗粒。
-
Patent Agency Ranking
6.发明申请METHOD AND APPARATUS FOR MODELING TARGET OBJECT TO REPRESENT SMOOTH SILHOUETTE 审中-公开用于建立目标对象到代表性的平滑硅胶的方法和装置公开(公告)号：US20160104319A1
公开(公告)日：2016-04-14
申请号：US14879273
申请日：2015-10-09
Applicant: Samsung Electronics Co., Ltd.
Inventor： Hwiryong JUNG , Nahyup KANG , Jiyeon KIM , Hyong Euk LEE
CPC classification number: G06T5/002 , G06T7/12 , G06T7/529 , G06T2207/20028
Abstract: Provided is a method of modeling a target object, that may obtain depth information from an image in which the target object is represented in a form of particles, obtain distance information between adjacent particles in the image, and detect a silhouette of the target object based on the depth information and the distance information between the adjacent particles in the image.
Abstract translation: 提供了一种对目标对象进行建模的方法，其可以从其中以粒子的形式表示目标对象的图像获得深度信息，获得图像中相邻粒子之间的距离信息，并基于目标对象的轮廓来检测 关于图像中的相邻颗粒之间的深度信息和距离信息。
-
公开(公告)号：US20160063140A1
公开(公告)日：2016-03-03
申请号：US14825755
申请日：2015-08-13
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Nahyup KANG , Jiyeon KIM , Hyong-euk LEE , Hwiryong JUNG
CPC classification number: G06F17/50 , G06F17/10 , G06F17/5009 , G06F2217/16
Abstract: Provided is a method and apparatus for modeling objects that may include detecting an adjacent area that shares modeled particles of a first object and modeled particles of a second object, calculating an action force between the first object and the second object in the adjacent area based on information stored for grid points of a grid defined with respect to the adjacent area, and modelling the first object and the second object based on the calculated action force.
Abstract translation: 提供了一种用于建模对象的方法和装置，其可以包括检测共享第一对象的建模粒子和第二对象的建模粒子的相邻区域，基于相邻区域中的第一对象和第二对象之间的动作力，基于 为相对于相邻区域定义的网格的网格点存储的信息，以及基于所计算的动作力对第一对象和第二对象进行建模。
-
公开(公告)号：US20240394964A1
公开(公告)日：2024-11-28
申请号：US18669048
申请日：2024-05-20
Inventor： Seung-Hwan BAEK , Seokjun CHOI , Seungwoo YOON , Seungyong LEE , Jinwoo PARK , Nahyup KANG , Jiyeon KIM
Abstract: A method of determining an illumination pattern includes constructing a dataset by estimating a first surface normal vector of a three-dimensional (3D) object from a first image obtained by capturing the 3D object of which surface normal information is known, the dataset including basis images of the 3D object; generating simulation images in which virtual illumination patterns, obtained based on a combination of the basis images, are applied to the 3D object; estimating a second surface normal vector of the 3D object, by reconstructing a surface normal using a photometric stereo technique based on the virtual illumination patterns and simulation images corresponding to the virtual illumination patterns; and training a neural network to determine an illumination pattern based on a difference between the first surface normal vector and the second surface normal vector.
-
公开(公告)号：US20240054716A1
公开(公告)日：2024-02-15
申请号：US18096972
申请日：2023-01-13
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Seokhwan Jang , Nahyup KANG , Jiyeon KIM , Hyewon MOON , Donghoon SAGONG , Minjung SON
Abstract: Disclosed are a method and device for representing rendered scenes. A data processing method of training a neural network model includes obtaining spatial information of sampling data, obtaining one or more volume-rendering parameters by inputting the spatial information of the sampling data to the neural network model, obtaining a regularization term based on a distribution of the volume-rendering parameters, performing volume rendering based on the volume-rendering parameters, and training the neural network model to minimize a loss function determined based on the regularization term and based on a difference between a ground truth image and an image that is estimated according to the volume rendering.
-
公开(公告)号：US20220164565A1
公开(公告)日：2022-05-26
申请号：US17529634
申请日：2021-11-18
Applicant: Samsung Electronics Co., Ltd.
Inventor： Weiming LI , Jiyeon KIM , Qiang WANG , Hyun Sung CHANG , Sunghoon HONG , Chao ZHANG
Abstract: A method with object detection includes: obtaining a first point cloud feature based on point cloud data of an image; and determining at least one object in the image based on the first point cloud feature.
-
-
-
-
-
-
-
-
-
Search Results
45
records
(took 0.025 seconds)
