公开(公告)号：US12198245B2

公开(公告)日：2025-01-14

申请号：US16879955

申请日：2020-05-21

Applicant: Samsung Electronics Co., Ltd.

Inventor： Inwoo Ha ,  Hyun Sung Chang ,  Nahyup Kang

IPC: G06T15/00 ,  G06N3/08 ,  G06T7/529 ,  G06T15/06 ,  G06T15/83 ,  G06T1/20

Abstract: A three-dimensional (3D) rendering method includes extracting sample points from a 3D scene, acquiring rendering result information for the sample points by rendering the sample points, and generating a rendering result image corresponding to an entire rendering based on the rendering result information for the sample points and feature information of the 3D scene.

公开(公告)号：US10810745B2

公开(公告)日：2020-10-20

申请号：US16103187

申请日：2018-08-14

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Nahyup Kang ,  KeeChang Lee ,  Inwoo Ha

IPC: G06T7/136 ,  G06K9/62 ,  G06N3/04 ,  G06N3/08

Abstract: A processor-implemented learning method for an image segmentation includes training first duplicate layers, as duplications of trained first layers of a pre-trained model, so that a second feature extracted from a target image by the trained first duplicate layers is matched to a first feature extracted from a training image by the trained first layers; regularizing the trained first duplicate layers so that a similarity between the first feature and a third feature extracted from the training image by the regularized first duplicate layers meets a threshold; and training second duplicate layers, as duplications of trained second layers of the pre-trained model, to be configured to segment the target image based on the regularized first duplicate layers, the trained second layer being configured to segment the training image.

公开(公告)号：US10261976B2

公开(公告)日：2019-04-16

申请号：US15191743

申请日：2016-06-24

Applicant: SAMSUNG ELECTRONICS CO., LTD. ,  Technische Universität München

Inventor： Nahyup Kang ,  Mengyu Chu ,  Nils Thuerey ,  Hyong Euk Lee ,  Donghoon Sagong

IPC: G06T3/40 ,  G06F17/14 ,  G06K9/62 ,  G06F17/50 ,  G06T7/11 ,  G06T7/44 ,  G06K9/00 ,  G06K9/46 ,  G06K9/68

Abstract: A method and apparatus for modeling smoke turbulence is disclosed. The method of modeling smoke turbulence includes detecting a turbulent area comprising smoke turbulence in a low-resolution image, and searching for a high-resolution patch matching the turbulent area in a memory that comprises high-resolution patches representing smoke turbulence extracted from high-resolution images. The method also models the smoke turbulence by synthesizing the retrieved patch to the low-resolution image.

公开(公告)号：US10127711B2

公开(公告)日：2018-11-13

申请号：US15179170

申请日：2016-06-10

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hwiryong Jung ,  Nahyup Kang ,  Jiyeon Kim ,  Donghoon Sagong ,  Hyong Euk Lee ,  Minjung Son ,  Inwoo Ha

IPC: G06T15/06 ,  G06T15/04 ,  G06T15/80 ,  G06T15/50

Abstract: A method of displaying caustics, the method includes determining intersection positions at which rays emitted from a light source pass through particles of a first object and meet a second object; applying caustic textures to the intersection positions; and rendering the first object using a caustic map based on a result of the applying caustic textures to the intersection positions.

公开(公告)号：US11295220B2

公开(公告)日：2022-04-05

申请号：US16535502

申请日：2019-08-08

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hyun Sung Chang ,  Wonhee Lee ,  Nahyup Kang

IPC: G06K9/00 ,  G06N5/04 ,  G06F16/532 ,  G06K9/62 ,  G06N3/04

Abstract: A processor-implemented method of implementing an attention mechanism in a neural network includes obtaining key-value coupling data determined based on an operation between new key data determined using a first nonlinear transformation for key data of an attention layer, and value data of the attention layer corresponding to the key data; determining new query data by applying a second nonlinear transformation to query data corresponding to input data of the attention layer; and determining output data of the attention layer based on an operation between the new query data and the key-value coupling data.

公开(公告)号：US10713397B2

公开(公告)日：2020-07-14

申请号：US14919184

申请日：2015-10-21

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hwiryong Jung ,  Nahyup Kang ,  Hyong Euk Lee ,  Jiyeon Kim

IPC: G06F30/20 ,  G06T13/00 ,  G06T13/60 ,  G06F111/10

Abstract: Provided is a method of modeling a target object, the method including obtaining information about the target object including an arrangement of particles including target particles, generating coarse particles by down-sampling the target particles, modeling a movement of the target object based on the coarse particles, and redefining the target particles based on a result of the modeling.

公开(公告)号：US10685241B2

公开(公告)日：2020-06-16

申请号：US15467190

申请日：2017-03-23

Applicant: Samsung Electronics Co., Ltd.

Inventor： Nahyup Kang ,  Young Hun Sung ,  KeeChang Lee

IPC: G06K9/00 ,  G06T7/70 ,  G06T7/77

Abstract: Disclosed are methods and apparatuses for indicating a lane, the method including detecting a lane marking from an input image, acquiring a bird's eye view image by applying an inverse perspective mapping to the detected lane marking, extracting control points corresponding to the lane marking from the bird's eye view image, and indicating a lane by re-projecting the control points to a space of the input image through an inverse transformation.

公开(公告)号：US10606966B2

公开(公告)日：2020-03-31

申请号：US14813459

申请日：2015-07-30

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jiyeon Kim ,  Nahyup Kang ,  Hyong Euk Lee ,  Hwiryong Jung

IPC: G06F17/10 ,  G06F17/50

Abstract: Provided are a method and a corresponding apparatus for modeling a deformable body including particles that define a strain energy generated by an external force with respect to a deformable body including particles, and control a displacement of the deformable body based on a volume of the particles corresponding to the displacement of the deformable body, where the displacement is determined based on the strain energy.

公开(公告)号：US20250054100A1

公开(公告)日：2025-02-13

申请号：US18404438

申请日：2024-01-04

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jaeyoung Moon ,  Nahyup Kang ,  Minjung Son ,  Hyeonseung Yu ,  Inwoo Ha ,  Seokpyo Hong

IPC: G06T3/40 ,  G06T3/18 ,  G06T5/50 ,  G06T7/20 ,  G06T15/00

Abstract: A supersampling method includes generating a current rendered image frame by performing jittered sampling on a three-dimensional (3D) scene, based on sub-pixels of low-resolution pixels for the current rendered image frame; generating a current warped image frame by warping a previous output image frame, based on a motion vector map corresponding to a difference between the current rendered image frame and a previous rendered image frame; generating a current shifted image frame by shifting pixels of the current warped image frame, based on a change in sampling positions based on the jittered sampling; and generating a current output image frame, based on the current rendered image frame and the current shifted image frame.

公开(公告)号：US10732004B2

公开(公告)日：2020-08-04

申请号：US15919432

申请日：2018-03-13

Applicant: Samsung Electronics Co., Ltd.

Inventor： Kyungboo Jung ,  Nahyup Kang ,  KeeChang Lee ,  Sunghoon Hong

IPC: G01C21/36 ,  G06T19/00 ,  G01C21/32 ,  G06F16/29 ,  G06T15/20

Abstract: A method and apparatus for displaying a virtual route estimates a position of a vehicle based on sensing data received asynchronously from sensors, and outputs a three-dimensional (3D) virtual route generated by registering a driving environment model corresponding to a driving environment of the vehicle and the position of the vehicle in map information.