公开(公告)号：US10825141B1

公开(公告)日：2020-11-03

申请号：US16843515

申请日：2020-04-08

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Youngo Park ,  Kwangpyo Choi ,  Yumi Sohn ,  Sungchan Kim ,  Myungjin Eom

IPC: G06T3/40 ,  G06N3/08 ,  H04N19/85

Abstract: Provided is a decoding apparatus including: a communication interface configured to receive AI encoding data generated as a result of artificial intelligence (AI) down-scaling and first encoding of an original image; a processor configured to divide the AI encoding data into image data and AI data; and an input/output (I/O) device, wherein the processor is further configured to: obtain a second image by performing first decoding on a first image obtained by performing AI down-scaling on the original image, based on the image data; and control the I/O device to transmit the second image and the AI data to an external apparatus. In some embodiments, the external apparatus performs an AI upscaling of the second image using the AI data, and displays the resulting third image.

公开(公告)号：US11997286B2

公开(公告)日：2024-05-28

申请号：US17675410

申请日：2022-02-18

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Minwoo Park ,  Minsoo Park ,  Kwangpyo Choi ,  Kiho Choi ,  Yinji Piao

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

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：US20230319319A1

公开(公告)日：2023-10-05

申请号：US18123623

申请日：2023-03-20

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Yinji PIAO ,  Kyungah Kim ,  Minsoo Park ,  Minwoo Park ,  Kwangpyo Choi

IPC: H04N19/91 ,  H04N19/174 ,  H04N19/70

CPC classification number: H04N19/91 ,  H04N19/174 ,  H04N19/70

Abstract: An entropy decoding method may include obtaining, from a bitstream, information about a slice type, based on an occurrence probability of a symbol, performing arithmetic decoding on a current symbol corresponding to a syntax element, when the information about the slice type indicates an I slice, determining a first scaling factor for updating the occurrence probability of the symbol by using a first function, wherein a value of the first function is determined based on a first threshold value, when the information about the slice type indicates a B or P slice, determining the first scaling factor by using a second function, wherein a value of the second function is determined based on a second threshold value, and by using the first scaling factor, updating the occurrence probability of the symbol.

公开(公告)号：US11756159B2

公开(公告)日：2023-09-12

申请号：US17331162

申请日：2021-05-26

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Youngo Park ,  Kwangpyo Choi ,  Yumi Sohn ,  Sungchan Kim ,  Myungjin Eom

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

CPC classification number: G06T3/4046 ,  G06T9/002 ,  H04N19/85 ,  G06N3/08 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Provided is a decoding apparatus including: a communication interface configured to receive AI encoding data generated as a result of artificial intelligence (AI) down-scaling and first encoding of an original image; a processor configured to divide the AI encoding data into image data and AI data; and an input/output (I/O) device, wherein the processor is further configured to: obtain a second image by performing first decoding on a first image obtained by performing AI down-scaling on the original image, based on the image data; and control the I/O device to transmit the second image and the AI data to an external apparatus. In some embodiments, the external apparatus performs an AI upscaling of the second image using the AI data, and displays the resulting third image.

公开(公告)号：US11676246B2

公开(公告)日：2023-06-13

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：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.

公开(公告)号：US20230085530A1

公开(公告)日：2023-03-16

申请号：US17895561

申请日：2022-08-25

Applicant: Samsung Electronics Co., Ltd.

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

IPC: H04N19/30 ,  H04N19/436 ,  H04N19/136 ,  H04N19/164

Abstract: Provided is an electronic device configured to participate in video conference by using artificial intelligence (AI), the electronic device including a display and a processor configured to execute one or more instructions. The processor configured to obtain, from a server, image data generated by first encoding first image related to another electronic device participating in video conference, and AI data related to AI downscaling from original image to first image, obtain second image corresponding to first image by performing first decoding on image data, determine whether to perform AI upscaling on second image, based on importance of the other electronic device, based on determining to perform AI upscaling, obtain third image by performing AI upscaling on second image through an upscaling deep neural network and provide third image to display, and based on determining not to perform AI upscaling, provide second image to display.

公开(公告)号：US20230041187A1

公开(公告)日：2023-02-09

申请号：US17882293

申请日：2022-08-05

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Quockhanh DINH ,  Kwangpyo Choi

IPC: H04N19/436 ,  H04N19/50 ,  H04N19/186 ,  H04N19/136 ,  H04N19/13 ,  H04N19/124 ,  H04N19/30 ,  G06N3/08 ,  G06N3/04

Abstract: A method of decoding an image based on cross-channel prediction using artificial intelligence (AI) includes obtaining cross-channel prediction information by applying feature data for cross-channel prediction to a neural-network-based cross-channel decoder, obtaining a predicted image of a chroma image by performing cross-channel prediction based on a reconstructed luma image and the cross-channel prediction information, obtaining a residual image of the chroma image by applying feature data of the chroma image to a neural-network-based chroma residual decoder, and reconstructing the chroma image based on the predicted image and the residual image.

公开(公告)号：US20220272372A1

公开(公告)日：2022-08-25

申请号：US17677498

申请日：2022-02-22

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Quockhanh DINH ,  Minwoo Park ,  Minsoo Park ,  Kwangpyo Choi

IPC: H04N19/51 ,  H04N19/137 ,  H04N19/17 ,  H04N19/43 ,  H04N19/91 ,  H04N19/124

Abstract: A method of reconstructing an optical flow by using artificial intelligence (AI), including obtaining, from a bitstream, feature data of a current residual optical flow for a current image; obtaining the current residual optical flow by applying the feature data of the current residual optical flow to a neural-network-based first decoder; obtaining a current predicted optical flow based on at least one of a previous optical flow, feature data of the previous optical flow, and feature data of a previous residual optical flow; and reconstructing a current optical flow based on the current residual optical flow and the current predicted optical flow.

公开(公告)号：US11200702B2

公开(公告)日：2021-12-14

申请号：US17147954

申请日：2021-01-13

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Quockhanh Dinh ,  Minseok Choi ,  Kwangpyo Choi

IPC: G06T9/00 ,  G06T3/40 ,  H04N19/85 ,  G06N3/02 ,  G06K9/62

Abstract: Provided is an artificial intelligence (AI) decoding apparatus including a memory storing one or more instructions; and a processor configured to execute the one or more instructions to, when an image is input to a second DNN including a plurality of layers, obtain first result values based on an operation between the image and a first filter kernel and obtain second result values based on an operation between the image and a second filter kernel, from a first layer including the first and second filter kernels from among the plurality of layers, perform normalization by transforming the first result values into first values by using a first scale factor, and, perform normalization by transforming the second result values into second values by using a second scale factor, transform the first values and the second values into integer values included in a preset range.