公开(公告)号：US20210390660A1

公开(公告)日：2021-12-16

申请号：US17240360

申请日：2021-04-26

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Sangwook BAEK ,  Yongsup PARK ,  Sangmi LEE ,  Youngo PARK ,  Kwangpyo CHOI

IPC: G06T3/40 ,  G06N3/04 ,  G06K9/46

Abstract: An image processing apparatus for performing image quality processing on an image includes a feature extraction network and an image quality processing network including one or more modulation blocks, wherein each of the one or more modulation blocks includes a convolution layer, a modulation layer, and an activation layer for processing the image.

公开(公告)号：US20210358083A1

公开(公告)日：2021-11-18

申请号：US17385995

申请日：2021-07-27

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Youngo PARK ,  Yumi SOHN ,  Myungjin EOM ,  Kwangpyo CHOI

IPC: G06T3/40 ,  H04L29/06 ,  H04N19/85

Abstract: A terminal for receiving streaming data may receive information of a plurality of different quality versions of an image content; request, based on the information, a server for a version of the image content from among the plurality of different quality versions of the image content; when the requested version of the image content and artificial intelligence (AI) data corresponding to the requested version of the image content are received, determines whether to perform AI upscaling on the received version of the image content, based on the AI data; and based on a result of the determining whether to perform AI upscaling, performs AI upscaling on the received version of the image content through a upscaling deep neural network (DNN) that is trained jointly with a downscaling DNN of the server.

公开(公告)号：US20200234469A1

公开(公告)日：2020-07-23

申请号：US16844124

申请日：2020-04-09

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Sunyoung JEON ,  Jaehwan KIM ,  Youngo PARK ,  Jongseok LEE ,  Minseok CHOI ,  Kwangpyo CHOI

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

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：US20200219232A1

公开(公告)日：2020-07-09

申请号：US16822665

申请日：2020-03-18

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Youngo PARK ,  Yumi SOHN ,  Myungjin EOM ,  Kwangpyo CHOI

IPC: G06T3/40 ,  H04L29/06

Abstract: A terminal for receiving streaming data may receive information of a plurality of different quality versions of an image content; request, based on the information, a server for a version of the image content from among the plurality of different quality versions of the image content; when the requested version of the image content and artificial intelligence (AI) data corresponding to the requested version of the image content are received, determines whether to perform AI upscaling on the received version of the image content, based on the AI data; and based on a result of the determining whether to perform AI upscaling, performs AI upscaling on the received version of the image content through a upscaling deep neural network (DNN) that is trained jointly with a downscaling DNN of the server.

公开(公告)号：US20200184685A1

公开(公告)日：2020-06-11

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

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：US20240259564A1

公开(公告)日：2024-08-01

申请号：US18609123

申请日：2024-03-19

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Minwoo PARK ,  Minsoo PARK ,  Kwangpyo CHOI ,  Kiho CHOI ,  Yinji PIAO

IPC: H04N19/139 ,  H04N19/105 ,  H04N19/11 ,  H04N19/172 ,  H04N19/176 ,  H04N19/52

CPC classification number: H04N19/139 ,  H04N19/105 ,  H04N19/11 ,  H04N19/172 ,  H04N19/176 ,  H04N19/52

Abstract: A method, performed by an image decoding apparatus, of decoding a motion vector, including obtaining information indicating a motion vector resolution of a current block from a bitstream; selecting a first neighboring block from among neighboring blocks adjacent to the current block, by using the obtained information indicating the motion vector resolution of the current block; based on the current block referring to a reference picture in a list 0, and the first neighboring block referring to the reference picture in the list 0, determining a prediction motion vector of the current block using a motion vector of the first neighboring block; based on the current block referring to the reference picture in the list 0 and the first neighboring block referring to a reference picture in a list 1, selecting a motion vector of a second neighboring block among the neighboring blocks as a basic motion vector, and determining the prediction motion vector of the current block using the determined basic motion vector; and determining a motion vector of the current block using the prediction motion vector of the current block.

公开(公告)号：US20230362367A1

公开(公告)日：2023-11-09

申请号：US18333067

申请日：2023-06-12

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Anubhav SINGH ,  Aviral AGRAWAL ,  Raj Narayana GADDE ,  H Keerthan BHAT ,  Yinji PIAO ,  Minwoo PARK ,  Kwangpyo CHOI

IPC: H04N19/119 ,  H04N19/117 ,  H04N19/80 ,  H04N19/42 ,  H04N19/176

CPC classification number: H04N19/119 ,  H04N19/117 ,  H04N19/80 ,  H04N19/42 ,  H04N19/176

Abstract: An example method for training AI models for in-loop filters includes generating a training dataset by passing a video through a codec pipeline, extracting one or more predefined block features from the training dataset, creating a plurality of clusters based on the extracted one or more predefined block features from the training dataset, dividing the plurality of clusters into a sub-plurality of clusters based on the extracted one or more predefined block features and an intra-cluster variation threshold, and supplying the sub-plurality of clusters separately into a plurality of AI models based on the extracted one or more predefined block features.

公开(公告)号：US20230245285A1

公开(公告)日：2023-08-03

申请号：US18131643

申请日：2023-04-06

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Quockhanh DINH ,  Kyonghwan JIN ,  Youngo PARK ,  Kwangpyo CHOI

IPC: G06T5/00 ,  H04N1/60 ,  G06V10/44 ,  G06V10/56 ,  G06V10/60

CPC classification number: G06T5/009 ,  H04N1/6077 ,  G06V10/44 ,  G06V10/56 ,  G06V10/60 ,  G06T2207/10024 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: A device and a method for generating an output image in which a subject has been captured are provided. A method of performing image processing may include: obtaining a raw image by a camera sensor of the device, by using a first processor configured to control the device; inputting the raw image to a first artificial intelligence (AI) model trained to scale image brightness, by using a second processor configured to perform AI-based image processing on the raw image; obtaining tone map data output from the first AI model, by using the second processor; and storing an output image generated based on the tone map data.

公开(公告)号：US20230044532A1

公开(公告)日：2023-02-09

申请号：US17880799

申请日：2022-08-04

Applicant: SAMSUNG ELECTRONICS CO, LTD.

Inventor： Quockhanh DINH ,  Kwangpyo CHOI ,  Minwoo PARK ,  Yinji PIAO

IPC: H04N19/86 ,  H04N19/80 ,  H04N19/182 ,  H04N19/187 ,  H04N19/117

Abstract: An image processing method and an image processing apparatus are provided to obtain input data for deblocking filtering based on deblocking filtering target pixels of at least one line perpendicular to a boundary line of blocks and encoding information about the deblocking filtering target pixels of at least one line, obtain a feature map of the input data by inputting the input data to a first neural network, obtain a deblocking filter coefficient by inputting the feature map to a second neural network, obtain a deblocking filter compensation value by inputting the feature map to a third neural network, obtain a deblocking filter strength by inputting the input data to a fourth neural network, obtain deblocking filtered pixels by performing deblocking filtering on the deblocking filtering target pixels of the at least one line using the deblocking filter coefficient, the deblocking filter compensation value, and the deblocking filter strength.

公开(公告)号：US20220405884A1

公开(公告)日：2022-12-22

申请号：US17893248

申请日：2022-08-23

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jaehwan KIM ,  Youngo PARK ,  Kwangpyo CHOI

IPC: G06T3/40 ,  H04N7/14 ,  G06T3/00 ,  H04N7/01

Abstract: Provided is a method of adaptively performing artificial intelligence (AI) downscaling on an image during a video telephone call of a user terminal. The method includes obtaining, from an opposite user terminal, AI upscaling support information of the opposite user terminal that is a target of a video telephone call, determining whether the user terminal is to perform AI downscaling on an original image, based on the AI upscaling support information, based on determining that the user terminal is to perform AI downscaling on the original image, obtaining a first image by AI downscaling the original image using a downscaling deep neural network (DNN), generating image data by performing first encoding on the first image, and transmitting AI data including information related to the AI downscaling and the image data.