公开(公告)号：US20230196651A1

公开(公告)日：2023-06-22

申请号：US17752351

申请日：2022-05-24

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Minjung SON ,  Hyun Sung CHANG

IPC: G06T15/00 ,  G06T15/50 ,  G06T15/10 ,  G06T15/04 ,  G06N3/04

CPC classification number: G06T15/005 ,  G06N3/04 ,  G06T15/04 ,  G06T15/10 ,  G06T15/506

Abstract: A method includes generating a first rendering based on input elements of an input scene, generating a second rendering by inputting a result of the first rendering to a generative machine learning model that is based on an artificial neural network (ANN), and generating a rendered output image based on the result of the first rendering and a result of the second rendering.

公开(公告)号：US20230177340A1

公开(公告)日：2023-06-08

申请号：US18103887

申请日：2023-01-31

Applicant: Samsung Electronics Co., Ltd.

Inventor： Minjung SON ,  Hyun Sung CHANG

IPC: G06N3/084 ,  G06F18/22 ,  G06F18/213

CPC classification number: G06N3/084 ,  G06F18/22 ,  G06F18/213

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：US20230169755A1

公开(公告)日：2023-06-01

申请号：US17994659

申请日：2022-11-28

Applicant: Samsung Electronics Co., Ltd.

Inventor： Bao HE ,  Hao WANG ,  Jiyeon KIM ,  Hyun Sung CHANG ,  Qiang WANG ,  Sunghoon HONG ,  Weiming LI

IPC: G06V10/771 ,  G06T5/20 ,  G06T7/70 ,  G06V10/25 ,  G06V10/44 ,  G06V10/80

CPC classification number: G06V10/771 ,  G06T5/20 ,  G06T7/70 ,  G06V10/25 ,  G06V10/44 ,  G06V10/806

Abstract: A processor-implement method with image processing includes: generating a feature map of a first image and detecting a target region in the first image based on the feature map; correcting the detected target region; and processing an object corresponding to the target region, based on the corrected target region.

公开(公告)号：US20230154170A1

公开(公告)日：2023-05-18

申请号：US17987060

申请日：2022-11-15

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hao WANG ,  Weiming LI ,  Qiang WANG ,  Jiyeon KIM ,  Hyun Sung CHANG ,  Sunghoon HONG

IPC: G06V10/80 ,  G06T17/00 ,  G06T7/50 ,  G06T7/62 ,  G06T7/70

CPC classification number: G06V10/806 ,  G06T17/00 ,  G06T7/50 ,  G06T7/62 ,  G06T7/70 ,  G06T2207/10024 ,  G06T2207/10028 ,  G06T2207/20016

Abstract: A method, apparatus, electronic device, and non-transitory computer-readable storage medium with multi-modal feature fusion are provided. The method includes generating three-dimensional (3D) feature information and two-dimensional (2D) feature information based on a color image and a depth image, generating fused feature information by fusing the 3D feature information and the 2D feature information based on an attention mechanism, and generating predicted image information by performing image processing based on the fused feature information.

公开(公告)号：US20220284663A1

公开(公告)日：2022-09-08

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 ,  G06T15/80

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：US20220180548A1

公开(公告)日：2022-06-09

申请号：US17545333

申请日：2021-12-08

Applicant: Samsung Electronics Co., Ltd.

Inventor： Weiming LI ,  Jiyeon KIM ,  Hyun Sung CHANG ,  Qiang WANG ,  Sunghoon HONG ,  Yang LIU ,  Hao WANG ,  Yueying KAO

IPC: G06T7/70 ,  G06T7/10 ,  G06T7/50 ,  G06V10/25

Abstract: A processor-implemented method with object pose estimation includes: determining an image feature corresponding to a point cloud of an input image; determining semantic segmentation information, instance mask information, and keypoint information of an object, based on the image feature; and estimating a pose of the object based on the semantic segmentation information, the instance mask information, and the keypoint information.

公开(公告)号：US20210398305A1

公开(公告)日：2021-12-23

申请号：US17462772

申请日：2021-08-31

Applicant: Samsung Electronics Co., Ltd.

Inventor： Wonhee LEE ,  Hyun Sung CHANG ,  Young Hun SUNG ,  KyungBoo JUNG

IPC: G06T7/593 ,  G06K9/46 ,  G06K9/62

Abstract: A stereo matching method includes obtaining a first feature map associated with a first view image and a second feature map associated with a second view image using a neural network model-based feature extractor, determining respective matching costs between a reference pixel of the first view image and candidate pixels of the second view image using the first feature map and the second feature map, and determining a pixel corresponding to the reference pixel among the candidate pixels based on the determined matching costs.

公开(公告)号：US20220198707A1

公开(公告)日：2022-06-23

申请号：US17537729

申请日：2021-11-30

Applicant: Samsung Electronics Co., Ltd.

Inventor： Weiming LI ,  Jiyeon KIM ,  Hyun Sung CHANG ,  Qiang WANG ,  Sunghoon HONG ,  Yang LIU ,  Yueying KAO ,  Hao WANG

IPC: G06T7/73 ,  G06T7/11 ,  G06T7/50

Abstract: A method with object pose estimation includes: obtaining an instance segmentation image and a normalized object coordinate space (NOCS) map by processing an input single-frame image using a deep neural network (DNN); obtaining a two-dimensional and three-dimensional (2D-3D) mapping relationship based on the instance segmentation image and the NOCS map; and determining a pose of an object instance in the input single-frame image based on the 2D-3D mapping relationship.

公开(公告)号：US20220148127A1

公开(公告)日：2022-05-12

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 ,  G06T7/60 ,  G06N3/08

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：US20190102678A1

公开(公告)日：2019-04-04

申请号：US15946800

申请日：2018-04-06

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hyun Sung CHANG ,  Donghoon SAGONG ,  Minjung SON

IPC: G06N3/08 ,  G06N3/04 ,  G06K9/62 ,  G06F17/18

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.