公开(公告)号：US12086940B2

公开(公告)日：2024-09-10

申请号：US17832847

申请日：2022-06-06

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Minjung Son ,  Hyun Sung Chang ,  Inwoo Ha

IPC: G06T17/00 ,  G06N3/045 ,  G06T17/20 ,  G06T19/20

CPC classification number: G06T17/205 ,  G06N3/045 ,  G06T19/20 ,  G06T2219/2004 ,  G06T2219/2024

Abstract: An image processing method is provided. The method includes generating appearance information corresponding to a canonical space defined by a cube including a plurality of regular grids in a first input image by implementing a first neural network, generating geometric information corresponding to a standard space in a second input image by implementing a second neural network, deforming the plurality of regular grids based on the generated geometric information, generating standardized image information by applying the appearance information to the plurality of deformed regular grids, and generating an output image based on the standardized image information.

公开(公告)号：US11023748B2

公开(公告)日：2021-06-01

申请号：US16295326

申请日：2019-03-07

Applicant: Samsung Electronics Co., Ltd.

Inventor： DongHoon Sagong ,  Hyun Sung Chang ,  Minjung Son

IPC: G06K9/00

Abstract: A method of estimating a position includes: determining a first rotation reference point based on localization information estimated for a target and map data; estimating a second rotation reference point from image data associated with a front view of the target; and correcting the localization information using a rotation parameter calculated based on the first rotation reference point and the second rotation reference point.

公开(公告)号：US10546392B2

公开(公告)日：2020-01-28

申请号：US15591378

申请日：2017-05-10

Applicant: Samsung Electronics Co., Ltd.

Inventor： Minjung Son ,  Hyun Sung Chang ,  Donghoon Sagong ,  Young Hun Sung

IPC: G06T7/90

Abstract: A method to process an image includes: determining a first specular reflection element from an input image based on a feature of chromaticity of pixels included in the input image; extracting a second specular reflection element from the first specular reflection element based on a feature of brightness of the pixels; and correcting the input image based on the second specular reflection element.

公开(公告)号：US11887269B2

公开(公告)日：2024-01-30

申请号：US17202899

申请日：2021-03-16

Applicant: Samsung Electronics Co., Ltd.

Inventor： Minjung Son ,  Hyun Sung Chang

IPC: G06T3/00 ,  G06T7/00 ,  G06T7/50 ,  G06N3/08 ,  G06T7/60

CPC classification number: G06T3/0012 ,  G06N3/08 ,  G06T7/0002 ,  G06T7/50 ,  G06T7/60 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: A method and apparatus for generating an image and for training an artificial neural network to generate an image are provided. The method of generating an image, including receiving input data comprising conditional information and image information, generating a synthesized image by applying the input data to an image generation neural network configured to maintain geometric information of the image information and to transform the remaining image information based on the conditional information, and outputting the synthesized image.

公开(公告)号：US11604964B2

公开(公告)日：2023-03-14

申请号：US16531522

申请日：2019-08-05

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Seungin Park ,  Minjung Son

IPC: G06N3/04 ,  G06F17/16 ,  G06F17/18 ,  G06K9/62

Abstract: A recognizer including a shared encoder to extract a feature of an input image in a source domain and a target domain; and a shared decoder to classify a class of an object included in the input image based on the feature of the input image, in the source domain and the target domain. A set of object classes of the source domain and a set of object classes of the target domain differ from each other.

公开(公告)号：US10755004B2

公开(公告)日：2020-08-25

申请号：US15241395

申请日：2016-08-19

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Donghoon Sagong ,  Nahyup Kang ,  Minjung Son ,  KeeChang Lee ,  Hyong Euk Lee ,  Heesae Lee

IPC: G06F30/20 ,  G06T13/60 ,  G06F111/08

Abstract: A method of modeling an object includes defining a state transition probability and a state of each of a plurality of particles forming the object; changing a state of a particle defined to be in a first state among the plurality of particles to a second state; applying a movement model to a particle defined to be in the second state among the plurality of particles; and changing a state of the particle defined to be in the second state to the first state based on the state transition probability.

公开(公告)号：US10242492B2

公开(公告)日：2019-03-26

申请号：US15208810

申请日：2016-07-13

Applicant: Samsung Electronics Co., Ltd.

Inventor： Inwoo Ha ,  Minsu Ahn ,  Minjung Son ,  Hyong Euk Lee

IPC: G06T15/60 ,  G06T1/20 ,  G06T17/10

Abstract: A shadow information storing method and apparatus is disclosed. The shadow information storing apparatus determines a shadow area through rendering a three-dimensional (3D) model based on light radiated from a reference virtual light source, determines a shadow feature value of a vertex of the 3D model based on a distance between a location of the vertex of the 3D model and the shadow area, and stores the determined shadow feature value.

公开(公告)号：US12198266B2

公开(公告)日：2025-01-14

申请号：US17487240

申请日：2021-09-28

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Inwoo Ha ,  Hyun Sung Chang ,  Minjung Son

IPC: G06T15/50 ,  G06T7/50 ,  G06T13/40 ,  G06T15/80 ,  G06V40/16

Abstract: A processor-implemented method includes: determining albedo data in a canonical space and depth data in the canonical space based on input image data including an object, using one or more neural network-based extraction models; generating deformed albedo data and deformed depth data by applying a target shape deformation value respectively to the albedo data and the depth data; generating resultant shaded data by performing shading based on the deformed depth data and a target illumination value; generating intermediate image data based on the resultant shaded data and the deformed albedo data; and generating reconstructed image data from the intermediate image data and the deformed depth data based on a target pose value.

公开(公告)号：US11586925B2

公开(公告)日：2023-02-21

申请号：US15946800

申请日：2018-04-06

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hyun Sung Chang ,  Donghoon Sagong ,  Minjung Son

IPC: G06V10/44 ,  G06N3/084 ,  G06N3/04 ,  G06F17/18 ,  G06K9/62

Abstract: Disclosed is a recognition and training method and apparatus. The apparatus may include a processor configured to input data to a neural network, determine corresponding to a multiclass output a mapping function of a first class and a mapping function of a second class, acquire a result of a loss function including a first probability component that changes correspondingly to a function value of the mapping function of the first class and a second probability component that changes contrastingly to a function value of the mapping function of the second class, determine a gradient of loss corresponding to the input data based on the result of the loss function, update a parameter of the neural network based on the determined gradient of loss for generating a trained neural network based on the updated parameter. The apparatus may input other data to the trained neural network, and indicate a recognition result.

公开(公告)号：US10607109B2

公开(公告)日：2020-03-31

申请号：US15592461

申请日：2017-05-11

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Donghoon Sagong ,  Minjung Son ,  Hyun Sung Chang ,  Young Hun Sung

IPC: G06K9/62 ,  G06K9/46 ,  G06T7/11 ,  G06T7/187 ,  G06K9/66 ,  G06N3/04 ,  G06N3/08

Abstract: Provided are method and apparatuses related to material recognition and training. A training apparatus for material recognition generates training data associated with a material by generating a texture image having a texture attribute from an object image and recognizing material information from the texture image using a material model.