公开(公告)号：US12132931B2

公开(公告)日：2024-10-29

申请号：US17876043

申请日：2022-07-28

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jongseok Lee ,  Youngo Park ,  Pilkyu Park ,  Yumi Sohn

IPC: H04N19/59 ,  G06N3/04 ,  G06T3/4046 ,  H04N19/172 ,  H04N19/61

CPC classification number: H04N19/59 ,  G06N3/04 ,  G06T3/4046 ,  H04N19/172 ,  H04N19/61

Abstract: Methods and apparatuses for image encoding and image decoding are provided. The image decoding method includes: obtaining deep neural network (DNN) update permission information indicating whether one or more pieces of DNN setting information are updated; based on the DNN update permission information indicating that the one or more pieces of the DNN setting information are updated, obtaining DNN update information necessary for determining one or more pieces of the DNN setting information that are updated; determining the one or more pieces of the updated DNN setting information according to the DNN update information; and obtaining a third image by performing artificial intelligence (AI) up-scaling on a second image according to the one or more pieces of the updated DNN setting information.

公开(公告)号：US20240054602A1

公开(公告)日：2024-02-15

申请号：US17893754

申请日：2022-08-23

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jongseok Lee ,  Pilkyu Park ,  Kwangpyo Choi ,  Jaehwan Kim ,  Youngo Park ,  Chaeeun Lee

IPC: G06T3/40 ,  G06V10/77 ,  G06V10/56 ,  G06T7/00

CPC classification number: G06T3/4046 ,  G06V10/7715 ,  G06V10/56 ,  G06T7/0002 ,  G06T2207/30168 ,  G06T2207/20081

Abstract: An electronic apparatus includes: a display; and a processor configured to: obtain a first image, identify an application used to obtain the first image, select neural network setting information corresponding to the identified application from among a plurality of pieces of neural network setting information, obtain a second image by artificial intelligence (AI)-upscaling the first image by using an upscaling neural network to which the selected neural network setting information is applied, and output the obtained second image via the display.

公开(公告)号：US11810332B2

公开(公告)日：2023-11-07

申请号：US17495050

申请日：2021-10-06

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jongseok Lee ,  Jaehwan Kim ,  Youngo Park

IPC: G06T9/00 ,  G06N3/08 ,  G06T3/40 ,  G06N3/082

CPC classification number: G06T9/002 ,  G06N3/082 ,  G06T3/4046

Abstract: An artificial intelligence (AI) decoding method including obtaining image data generated from performing first encoding on a first image and AI data related to AI down-scaling of at least one original image related to the first image; obtaining a second image corresponding to the first image by performing first decoding on the image data; obtaining, based on the AI data, deep neural network (DNN) setting information for performing AI up-scaling of the second image; and generating a third image by performing the AI up-scaling on the second image via an up-scaling DNN operating according to the obtained DNN setting information. The DNN setting information is DNN information updated for performing the AI up-scaling of at least one second image via joint training of the up-scaling DNN and a down-scaling DNN used for the AI down-scaling.

公开(公告)号：US20220138904A1

公开(公告)日：2022-05-05

申请号：US17575691

申请日：2022-01-14

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jaehwan Kim ,  Jongseok Lee ,  Sunyoung Jeon ,  Kwangpyo Choi ,  Minseok Choi ,  Quockhanh Dinh ,  Youngo Park

IPC: G06T3/40 ,  G06T9/00 ,  G06N3/08 ,  H04N19/85 ,  G06N20/10

Abstract: An artificial intelligence (AI) decoding apparatus includes a memory storing one or more instructions, and a processor configured to execute the stored one or more instructions, to obtain image data corresponding to a first image that is encoded, obtain a second image corresponding to the first image by decoding the obtained image data, determine whether to perform AI up-scaling of the obtained second image, based on the AI up-scaling of the obtained second image being determined to be performed, obtain a third image by performing the AI up-scaling of the obtained second image through an up-scaling deep neural network (DNN), and output the obtained third image, and based on the AI up-scaling of the obtained second image being determined to be not performed, output the obtained second image.

公开(公告)号：US11164340B2

公开(公告)日：2021-11-02

申请号：US17180358

申请日：2021-02-19

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jongseok Lee ,  Jaehwan Kim ,  Youngo Park

IPC: G06T9/00 ,  G06N3/08 ,  G06T3/40

Abstract: An artificial intelligence (AI) decoding method including obtaining image data generated from performing first encoding on a first image and AI data related to AI down-scaling of at least one original image related to the first image; obtaining a second image corresponding to the first image by performing first decoding on the image data; obtaining, based on the AI data, deep neural network (DNN) setting information for performing AI up-scaling of the second image; and generating a third image by performing the AI up-scaling on the second image via an up-scaling DNN operating according to the obtained DNN setting information. The DNN setting information is DNN information updated for performing the AI up-scaling of at least one second image via joint training of the up-scaling DNN and a down-scaling DNN used for the AI down-scaling.

公开(公告)号：US10825205B2

公开(公告)日：2020-11-03

申请号：US16793605

申请日：2020-02-18

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jaehwan Kim ,  Jongseok Lee ,  Sunyoung Jeon ,  Kwangpyo Choi ,  Minseok Choi ,  Quockhanh Dinh ,  Youngo Park

IPC: G06T9/00 ,  G06T3/40 ,  H04N19/85

Abstract: Provided is an artificial intelligence (AI) decoding apparatus includes: a memory storing one or more instructions; and a processor configured to execute the one or more instructions stored in the memory, the processor is configured to: obtain AI data related to AI down-scaling an original image to a first image; obtain image data corresponding to an encoding result on the first image; obtain a second image corresponding to the first image by performing a decoding on the image data; obtain deep neural network (DNN) setting information among a plurality of DNN setting information from the AI data; and obtain, by an up-scaling DNN, a third image by performing the AI up-scaling on the second image, the up-scaling DNN being configured with the obtained DNN setting information, wherein the plurality of DNN setting information comprises a parameter used in the up-scaling DNN, the parameter being obtained through joint training of the up-scaling DNN and a down-scaling DNN, and wherein the down-scaling DNN is used to obtain the first image from the original image.

公开(公告)号：US10817989B2

公开(公告)日：2020-10-27

申请号：US16831521

申请日：2020-03-26

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jaehwan Kim ,  Jongseok Lee ,  Sunyoung Jeon ,  Kwangpyo Choi ,  Minseok Choi ,  Quockhanh Dinh ,  Youngo Park

IPC: G06T3/40 ,  G06T9/00 ,  G06N3/08 ,  H04N19/85 ,  G06N20/10

Abstract: An artificial intelligence (AI) decoding apparatus includes a memory storing one or more instructions, and a processor configured to execute the stored one or more instructions, to obtain image data corresponding to a first image that is encoded, obtain a second image corresponding to the first image by decoding the obtained image data, determine whether to perform AI up-scaling of the obtained second image, based on the AI up-scaling of the obtained second image being determined to be performed, obtain a third image by performing the AI up-scaling of the obtained second image through an up-scaling deep neural network (DNN), and output the obtained third image, and based on the AI up-scaling of the obtained second image being determined to be not performed, output the obtained second image.

公开(公告)号：US20250118600A1

公开(公告)日：2025-04-10

申请号：US18984957

申请日：2024-12-17

Applicant: Samsung Electronics Co., Ltd.

Inventor： Uihyoung Lee ,  Honyun Park ,  Jongseok Lee ,  Sewan Kim ,  Taesung Lee

IPC: H01L21/768 ,  C23C14/04

Abstract: A method of fabricating a semiconductor device includes forming a dielectric layer on a lower structure. The method includes forming an opening to penetrate through the dielectric layer. The method includes alternately repeating a first operation, in which a first sputtering deposition process is performed to form a first metal pattern in the opening, and a second operation, in which a second sputtering deposition process is performed to form a second metal pattern in the opening, two or more times to form a first metal layer. The method includes forming a second metal layer on the first metal layer in an electroplating manner, and planarizing the first and second metal layers. Moreover, first and second process times, during which the first sputtering deposition process and the second sputtering deposition process, respectively, are performed, are each about five seconds or less.

公开(公告)号：US20230386193A1

公开(公告)日：2023-11-30

申请号：US18224756

申请日：2023-07-21

Applicant: Samsung Electronics CO., LTD.

Inventor： Chaeeun LEE ,  Pilkyu Park ,  Jaehwan Kim ,  Heechul Yang ,  Jongseok Lee ,  Youngo Park ,  Kwangpyo Chol

IPC: G06V10/82 ,  H04N23/60 ,  H04N23/667 ,  G06T5/00

CPC classification number: G06V10/82 ,  H04N23/64 ,  H04N23/667 ,  G06T5/002

Abstract: A method of processing an image by using a neural network model includes obtaining an image captured via an image sensor, identifying a shooting context of the image, selecting a neural network model included in at least one of an image reconstruction module or an image correction module according to the shooting context, and processing the image by using the selected neural network model.

公开(公告)号：US11663747B2

公开(公告)日：2023-05-30

申请号：US17383533

申请日：2021-07-23

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jaehwan Kim ,  Jongseok Lee ,  Sunyoung Jeon ,  Kwangpyo Choi ,  Minseok Choi ,  Quockhanh Dinh ,  Youngo Park

IPC: G06T9/00 ,  G06T3/40 ,  H04N19/85 ,  G06V10/82

CPC classification number: G06T9/002 ,  G06T3/4046 ,  G06V10/82 ,  H04N19/85 ,  G06T2207/20081

Abstract: Provided is an artificial intelligence (AI) decoding apparatus includes: a memory storing one or more instructions; and a processor configured to execute the one or more instructions stored in the memory, the processor is configured to: obtain AI data related to AI down-scaling an original image to a first image; obtain image data corresponding to an encoding result on the first image; obtain a second image corresponding to the first image by performing a decoding on the image data; obtain deep neural network (DNN) setting information among a plurality of DNN setting information from the AI data; and obtain, by an up-scaling DNN, a third image by performing the AI up-scaling on the second image, the up-scaling DNN being configured with the obtained DNN setting information, wherein the plurality of DNN setting information comprises a parameter used in the up-scaling DNN, the parameter being obtained through joint training of the up-scaling DNN and a down-scaling DNN, and wherein the down-scaling DNN is used to obtain the first image from the original image.