公开(公告)号：US12175706B2

公开(公告)日：2024-12-24

申请号：US17699657

申请日：2022-03-21

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hyewon Moon ,  Jiyeon Kim ,  Minjung Son

IPC: G06T7/73 ,  G06N3/08

Abstract: A method with global localization includes: extracting a feature by applying an input image to a first network; estimating a coordinate map corresponding to the input image by applying the extracted feature to a second network; and estimating a pose corresponding to the input image based on the estimated coordinate map, wherein either one or both of the first network and the second network is trained based on either one or both of: a first generative adversarial network (GAN) loss determined based on a first feature extracted by the first network based on a synthetic image determined by three-dimensional (3D) map data and a second feature extracted by the first network based on a real image; and a second GAN loss determined based on a first coordinate map estimated by the second network based on the first feature and a second coordinate map estimated by the second network based on the second feature.

公开(公告)号：US12159232B2

公开(公告)日：2024-12-03

申请号：US18103887

申请日：2023-01-31

Applicant: Samsung Electronics Co., Ltd.

Inventor： Minjung Son ,  Hyun Sung Chang

IPC: G06N3/08 ,  G06F18/213 ,  G06F18/22 ,  G06K9/62 ,  G06N3/084

Abstract: A processor-implemented neural network operating method, the operating method comprising obtaining a neural network pre-trained in a source domain and a first style feature of the source domain, extracting a second style feature of a target domain from received input data of the target domain, using the neural network, performing domain adaptation of the input data, by performing style matching of the input data based on the first style feature of the source domain and the second style feature of the target domain, and processing the style-matched input data, using the neural network.

公开(公告)号：US11651597B2

公开(公告)日：2023-05-16

申请号：US17316957

申请日：2021-05-11

Applicant: Samsung Electronics Co., Ltd.

Inventor： DongHoon Sagong ,  Hyun Sung Chang ,  Minjung Son

IPC: G06V20/58 ,  G06V20/56

CPC classification number: G06V20/588

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：US11651053B2

公开(公告)日：2023-05-16

申请号：US17190965

申请日：2021-03-03

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Minjung Son ,  Hyun Sung Chang

IPC: G06F18/21 ,  G06V10/22 ,  G06F18/214 ,  G06N3/08 ,  G10L25/30

CPC classification number: G06F18/2193 ,  G06F18/2148 ,  G06N3/08 ,  G06V10/22 ,  G10L25/30

Abstract: A processor-implemented method using a neural network (NN) includes: receiving input data; and determining information inferred from the input data based on state information about a state in which the NN is activated in response to the input data, wherein an embedding vector generated by encoding the input data using at least a portion of the NN comprises information used to reconstruct a first partial region of the input data with a first accuracy and to reconstruct a second partial region of the input data with a second accuracy, and wherein the first partial region is adaptively determined based on either one or both of the inferred information and the embedding vector.

公开(公告)号：US11531897B2

公开(公告)日：2022-12-20

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 ,  G06N3/08 ,  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：US11176719B2

公开(公告)日：2021-11-16

申请号：US16371305

申请日：2019-04-01

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hyun Sung Chang ,  Minjung Son ,  Donghoon Sagong ,  Wonhee Lee ,  Kyungboo Jung

IPC: G06T11/60 ,  G06T7/11 ,  G06T7/73 ,  G01C21/36 ,  G06K9/62

Abstract: Localization apparatuses and methods are disclosed where a localization apparatus extracts a feature of an object from an input image, generates an image in which the object is projected with respect to localization information of a device based on map data, and evaluates the localization information based on feature values corresponding to vertices included in a projection image.

公开(公告)号：US10691971B2

公开(公告)日：2020-06-23

申请号：US15492772

申请日：2017-04-20

Applicant: SAMSUNG ELECTRONICS CO., LTD.

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

IPC: G06K9/46 ,  G06K9/32 ,  G06K9/62 ,  G06N3/08 ,  G06N3/04

Abstract: A method includes actuating a processor to apply an input image to a feature extractor including a plurality of layers, determine a third feature vector based on first feature vectors of an input image output by a first layer included in a feature extractor and second feature vectors of the input image output by a second layer in the feature extractor, and identify an object in the input image based on the third feature vector.

公开(公告)号：US10332301B2

公开(公告)日：2019-06-25

申请号：US15343972

申请日：2016-11-04

Applicant: SAMSUNG ELECTRONICS CO., LTD.

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

IPC: G06T15/80 ,  G06T15/00 ,  G06T15/55 ,  G06T15/60 ,  G06T17/20

Abstract: A three-dimensional (3D) rendering method and apparatus is disclosed. The 3D rendering apparatus may determine a select shading point in a 3D scene on which shading is to be performed, perform the shading on the determined shading point, and determine shading information of the 3D scene based on a result of the shading performed on the determined shading point.

公开(公告)号：US10140755B2

公开(公告)日：2018-11-27

申请号：US15076817

申请日：2016-03-22

Applicant: Samsung Electronics Co., Ltd.

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

IPC: G06T15/80 ,  G06T15/00 ,  G06T17/20

Abstract: A three-dimensional (3D) rendering method and apparatus is disclosed. The 3D rendering apparatus determines a vertex for a first shading from among vertices of a 3D model based on characteristic information of the 3D model, performs the first shading on the determined vertex, determines a pixel area for a second shading based on reference information indicating whether the first shading is applied to at least one vertex comprising the pixel area, performs the second shading on the determined pixel area, and generates a rendered image based on the first shading and the second shading.