公开(公告)号：US10825204B2

公开(公告)日：2020-11-03

申请号：US16785092

申请日：2020-02-07

Applicant: SAMSUNG ELECTRONICS CO., LTD.

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

IPC: G06T9/00 ,  G06T5/00 ,  G06T5/50 ,  G06T3/40 ,  G06N3/04 ,  G06N3/08 ,  G06T5/20 ,  H04N19/86

Abstract: Provided is an artificial intelligence (AI) encoding apparatus including a memory storing one or more instructions, and a processor configured to execute the one or more instructions stored in the memory to obtain a first image by performing AI down-scaling on an original image through a deep neural network (DNN) for down-scaling, obtain artifact information indicating an artifact region in the first image, perform post-processing to change a pixel value of a pixel in the first image, based on the artifact information, and obtain image data corresponding to a result of encoding of the post-processed first image, and AI data including the artifact information.

公开(公告)号：US10817985B2

公开(公告)日：2020-10-27

申请号：US16656812

申请日：2019-10-18

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：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：US11720997B2

公开(公告)日：2023-08-08

申请号：US16599291

申请日：2019-10-11

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Minseok Choi ,  Kwangpyo Choi ,  Jaehwan Kim

IPC: G06T3/40 ,  H04N19/42 ,  H04N19/33 ,  G06N3/02 ,  H04N19/85

CPC classification number: G06T3/4046 ,  G06N3/02 ,  H04N19/33 ,  H04N19/42 ,  H04N19/85

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 downscaled from an original image by using first parameters of a first filter kernel included in a first deep neural network (DNN), reconstruct a second image corresponding to the first image, based on the obtained image data, and obtain a third image that is upscaled from the reconstructed second image, by performing an operation between the reconstructed second image and second parameters of a second filter kernel included in a second DNN corresponding to the first DNN. Each of the second parameters is represented by a product of a scale factor and one among integer values, and each of the integer values is 0 or ±2n, where n is an integer.

公开(公告)号：US11709593B2

公开(公告)日：2023-07-25

申请号：US16925489

申请日：2020-07-10

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Wonsuk Chung ,  Sunghyun Park ,  Soonyong Cho ,  Jaehwan Kim ,  Jisup Lee

IPC: G06F3/04886

CPC classification number: G06F3/04886

Abstract: Disclosed are an electronic apparatus and a method of controlling the same. The electronic apparatus includes a camera, a display, a memory, and a processor configured to execute at least one instruction to: detect a plurality of fingers in a plurality of first image frames obtained through the camera and, in response to an identification that a pose of the plurality of detected fingers corresponds to a trigger pose, enter a character input mode, detect a first motion of a finger among the plurality of fingers in a plurality of second image frames obtained through in the character input mode, identify a key corresponding to the first motion, from among a plurality of keys mapped to the finger, based on a position of the finger by the first motion and a reference point set to the finger, and control the display to display information corresponding to the identified key.

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：US11314915B2

公开(公告)日：2022-04-26

申请号：US16859323

申请日：2020-04-27

Applicant: Samsung Electronics Co., Ltd.

Inventor： Jin Kim ,  Byungmoo Kim ,  Jaehwan Kim ,  Junsu Jeon

IPC: G06F30/30 ,  G06F30/392 ,  G06F30/398

Abstract: A method of designing a layout of a semiconductor device includes determining from among a plurality of integrated circuit (IC) blocks in the semiconductor device a selection IC block for which a layout is to be changed, changing an spacing interval at which fin structures included in the selection IC block are spaced apart from each other in a first direction from a first spacing interval to a second spacing interval, and determining in the selection IC block locations of source/drain regions connected to the fin structures spaced apart from each other in the first direction at the second spacing interval.

公开(公告)号：US11270469B2

公开(公告)日：2022-03-08

申请号：US17333845

申请日：2021-05-28

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Chaeeun Lee ,  Jaehwan Kim ,  Youngo Park

IPC: G06T3/40 ,  G06N3/04 ,  G06N3/08 ,  G06T9/00

Abstract: An apparatus for performing artificial intelligence (AI) encoding on an image includes: a memory storing one or more instructions; and a processor configured to execute the one or more instructions stored in the memory to: determine a resolution of an original image; when the resolution of the original image is higher than a predetermined value, obtain a first image by performing AI downscaling on the original image via a downscaling deep neural network (DNN); when the resolution of the original image is lower than or equal to the predetermined value, obtain a first image by performing AI one-to-one preprocessing on the original image via a one-to-one preprocessing DNN for upscaling; generate image data by performing first encoding on the first image; and transmit the image data and AI data including information related to the AI downscaling or information related to the AI one-to-one preprocessing.

公开(公告)号：US11200639B1

公开(公告)日：2021-12-14

申请号：US17237775

申请日：2021-04-22

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jaehwan Kim ,  Youngo Park ,  Kwangpyo Choi

IPC: G06T3/40 ,  G06N3/04 ,  G06N3/08 ,  G06T9/00

Abstract: An artificial intelligence (AI) encoding apparatus includes a processor configured to execute one or more instructions stored in the AI encoding apparatus to: input, to a downscale deep neural network (DNN), a first reduced image downscaled from an original image and a reduction feature map having a resolution lower than a resolution of the original image; obtain a first image AI-downscaled from the original image in the downscale DNN; generate image data by performing a first encoding process on the first image; and output the image data.