公开(公告)号：US10819993B2

公开(公告)日：2020-10-27

申请号：US16860563

申请日：2020-04-28

Applicant: SAMSUNG ELECTRONICS CO., LTD.

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

IPC: H04N19/146 ,  H04N19/172 ,  H04N19/30 ,  H04N19/42 ,  H04N19/70

Abstract: Provided is a computer-recordable recording medium having stored thereon a video file including artificial intelligence (AI) encoding data, wherein the AI encoding data includes: image data including encoding information of a low resolution image generated by AI down-scaling a high resolution image; and AI data about AI up-scaling of the low resolution image reconstructed according to the image data, wherein the AI data includes: AI target data indicating whether AI up-scaling is to be applied to at least one frame; and AI supplementary data about up-scaling deep neural network (DNN) information used for AI up-scaling of the at least one frame from among a plurality of pieces of pre-set default DNN configuration information, when AI up-scaling is applied to the at least one frame.

公开(公告)号：US12223617B2

公开(公告)日：2025-02-11

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: G06T3/4046 ,  G06T7/00 ,  G06V10/56 ,  G06V10/77

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：US11159809B2

公开(公告)日：2021-10-26

申请号：US17080827

申请日：2020-10-26

Applicant: SAMSUNG ELECTRONICS CO., LTD.

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

IPC: H04N19/132 ,  H04N19/146 ,  H04N19/172 ,  H04N19/182 ,  H04N19/30 ,  H04N19/42 ,  H04N19/59 ,  H04N19/70 ,  H04N19/85

Abstract: Provided is a computer-recordable recording medium having stored thereon a video file including artificial intelligence (AI) encoding data, wherein the AI encoding data includes: image data including encoding information of a low resolution image generated by AI down-scaling a high resolution image; and AI data about AI up-scaling of the low resolution image reconstructed according to the image data, wherein the AI data includes: AI target data indicating whether AI up-scaling is to be applied to at least one frame; and AI supplementary data about up-scaling deep neural network (DNN) information used for AI up-scaling of the at least one frame from among a plurality of pieces of pre-set default DNN configuration information, when AI up-scaling is applied to the at least one frame.

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：US11405637B2

公开(公告)日：2022-08-02

申请号：US17081364

申请日：2020-10-27

Applicant: SAMSUNG ELECTRONICS CO., LTD.

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

IPC: H04N19/59 ,  G06T3/40 ,  H04N19/61 ,  H04N19/172 ,  G06N3/04

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：US10819992B2

公开(公告)日：2020-10-27

申请号：US16743613

申请日：2020-01-15

Applicant: SAMSUNG ELECTRONICS CO., LTD.

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

IPC: H04N19/132 ,  H04N19/146 ,  H04N19/172 ,  H04N19/182 ,  H04N19/30 ,  H04N19/42 ,  H04N19/59 ,  H04N19/70 ,  H04N19/85

Abstract: Provided is a computer-recordable recording medium having stored thereon a video file including artificial intelligence (AI) encoding data, wherein the AI encoding data includes: image data including encoding information of a low resolution image generated by AI down-scaling a high resolution image; and AI data about AI up-scaling of the low resolution image reconstructed according to the image data, wherein the AI data includes: AI target data indicating whether AI up-scaling is to be applied to at least one frame; and AI supplementary data about up-scaling deep neural network (DNN) information used for AI up-scaling of the at least one frame from among a plurality of pieces of pre-set default DNN configuration information, when AI up-scaling is applied to the at least one frame.

公开(公告)号：US11647210B2

公开(公告)日：2023-05-09

申请号：US17498859

申请日：2021-10-12

Applicant: SAMSUNG ELECTRONICS CO., LTD.

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

IPC: G06N3/04 ,  G06N3/08 ,  G06T3/40 ,  H04N19/132 ,  H04N19/146 ,  H04N19/172 ,  H04N19/182 ,  H04N19/184 ,  H04N19/30 ,  H04N19/42 ,  H04N19/59 ,  H04N19/70 ,  H04N19/85 ,  H04N19/50

CPC classification number: H04N19/30 ,  H04N19/146 ,  H04N19/172 ,  H04N19/42 ,  H04N19/70

Abstract: Provided is a computer-recordable recording medium having stored thereon a video file including artificial intelligence (AI) encoding data, wherein the AI encoding data includes: image data including encoding information of a low resolution image generated by AI down-scaling a high resolution image; and AI data about AI up-scaling of the low resolution image reconstructed according to the image data, wherein the AI data includes: AI target data indicating whether AI up-scaling is to be applied to at least one frame; and AI supplementary data about up-scaling deep neural network (DNN) information used for AI up-scaling of the at least one frame from among a plurality of pieces of pre-set default DNN configuration information, when AI up-scaling is applied to the at least one frame.

公开(公告)号：US11190782B2

公开(公告)日：2021-11-30

申请号：US17080827

申请日：2020-10-26

Applicant: SAMSUNG ELECTRONICS CO., LTD.

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

IPC: H04N19/132 ,  H04N19/146 ,  H04N19/172 ,  H04N19/182 ,  H04N19/30 ,  H04N19/42 ,  H04N19/59 ,  H04N19/70 ,  H04N19/85

Abstract: Provided is a computer-recordable recording medium having stored thereon a video file including artificial intelligence (AI) encoding data, wherein the AI encoding data includes: image data including encoding information of a low resolution image generated by AI down-scaling a high resolution image; and AI data about AI up-scaling of the low resolution image reconstructed according to the image data, wherein the AI data includes: AI target data indicating whether AI up-scaling is to be applied to at least one frame; and AI supplementary data about up-scaling deep neural network (DNN) information used for AI up-scaling of the at least one frame from among a plurality of pieces of pre-set default DNN configuration information, when AI up-scaling is applied to the at least one frame.

公开(公告)号：US11122267B2

公开(公告)日：2021-09-14

申请号：US16671286

申请日：2019-11-01

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Pilkyu Park ,  Kiljong Kim ,  Kwangpyo Choi

IPC: H04N19/124 ,  H04N19/196 ,  H04N19/119 ,  G06K9/62 ,  G06N3/08 ,  G06N20/10 ,  H04N19/176

Abstract: Provided is a method of encoding an image, the method including: obtaining a plurality of patches from the image; obtaining a plurality of transform coefficient groups respectively corresponding to the plurality of patches; inputting, to a machine learning model, input values corresponding to transform coefficients included in each of the plurality of transform coefficient groups; quantizing transform coefficients corresponding to the image by using a quantization table output from the machine learning model; and generating a bitstream including data generated as a result of the quantizing and information about the quantization table.

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.