公开(公告)号：US20200175650A1

公开(公告)日：2020-06-04

申请号：US16781083

申请日：2020-02-04

Applicant: SAMSUNG ELECTRONICS CO., LTD.

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

IPC: G06T3/40 ,  G06T7/00 ,  G06T9/00 ,  G06N3/08 ,  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：US20200126262A1

公开(公告)日：2020-04-23

申请号：US16570057

申请日：2019-09-13

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：US20200126186A1

公开(公告)日：2020-04-23

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 ,  G06T7/00 ,  G06N3/08 ,  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：US20240064336A1

公开(公告)日：2024-02-22

申请号：US18237109

申请日：2023-08-23

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Kyungah KIM ,  Quockhanh DINH ,  Minsoo PARK ,  Minwoo PARK ,  Kwangpyo CHOI ,  Yinji PIAO

IPC: H04N19/66 ,  H04N19/132 ,  H04N19/105 ,  H04N19/176

CPC classification number: H04N19/66 ,  H04N19/132 ,  H04N19/105 ,  H04N19/176

Abstract: A method of decoding an image, including obtaining a motion vector of a current block; obtaining a preliminary prediction block based on a reference block indicated by the motion vector in a reference image; obtaining a final prediction block for the current block by applying, to a neural network, at least one of a picture order count (POC) map including a POC difference between the reference image and a current image including the current block, the preliminary prediction block, and a quantization error map; and reconstructing the current block based on the final prediction block and a residual block obtained from a bitstream, wherein sample values of the quantization error map are calculated based on a quantization parameter for the reference block

公开(公告)号：US20230351719A1

公开(公告)日：2023-11-02

申请号：US18315072

申请日：2023-05-10

Applicant: Samsung Electronics Co., Ltd.

Inventor： Eega Revanth RAJ ,  Sai Karthikey PENTAPATI ,  Raj Narayana GADDE ,  Anushka GUPTA ,  Dongkyu KIM ,  Kwangpyo CHOI

IPC: G06V10/42 ,  G06V10/44 ,  G06V10/94

CPC classification number: G06V10/42 ,  G06V10/44 ,  G06V10/94

Abstract: An electronic device for determining global attention in a deep learning model is provided. The electronic device includes a hardware accelerator, a low-complex global attention generator, a parallel switch, and a series switch. The hardware accelerator is configured to process each tile of a full-frame image and the low complex global attention generator is configured to generate a channel attention map of the full-frame image. The parallel switch is configured to bypass a connection of the channel attention map with the hardware accelerator and a series switch, configured to gate the connection of the channel attention map with the hardware accelerator.

公开(公告)号：US20230247212A1

公开(公告)日：2023-08-03

申请号：US18133369

申请日：2023-04-11

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Quockhanh DINH ,  Kwangpyo CHOI

IPC: H04N19/42 ,  H04N19/137 ,  H04N19/52

CPC classification number: H04N19/42 ,  H04N19/137 ,  H04N19/52

Abstract: An image decoding method includes obtaining feature data of a current optical flow and feature data of a current residual image from a bitstream; obtaining the current optical flow and first weight data by applying the feature data of the current optical flow to an optical flow decoder; obtaining the current residual image by applying the feature data of the current residual image to a residual decoder; obtaining a preliminary prediction image from the previous reconstructed image, based on the current optical flow; obtaining a final prediction image by applying sample values of the first weight data to sample values of the preliminary prediction image; and obtaining a current reconstructed image corresponding to the current image by combining the final prediction image with the current residual image.

公开(公告)号：US20230145525A1

公开(公告)日：2023-05-11

申请号：US17983843

申请日：2022-11-09

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Quockhanh DINH ,  Kwangpyo CHOI

IPC: G06T9/00 ,  G06T3/40

CPC classification number: G06T9/002 ,  G06T3/4046

Abstract: An image decoding method using artificial intelligence (AI), including obtaining, from a bitstream, a current optical flow and correction data which are generated based on a current predicted image and a current image; obtaining the current predicted image based on a previous reconstructed image and the current optical flow; obtaining feature data of the current predicted image by applying the current predicted image to a neural network-based predicted image encoder; and obtaining a current reconstructed image corresponding to the current image by applying the correction data and the feature data of the current predicted image to a neural network-based image decoder

公开(公告)号：US20230145364A1

公开(公告)日：2023-05-11

申请号：US17984063

申请日：2022-11-09

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Minsoo PARK ,  Minwoo PARK ,  Ilkoo KIM ,  Kwangpyo CHOI

IPC: H04N19/137 ,  H04N19/105 ,  H04N19/176

CPC classification number: H04N19/137 ,  H04N19/105 ,  H04N19/176

Abstract: Provided are a video decoding method and apparatus for obtaining, from a bitstream, information about a first motion vector of a current block, determining, based on the information about the first motion vector, the first motion vector, determining a candidate list including a plurality of candidate prediction motion vectors for determining a second motion vector of the current block, determining, based on a distance between each of the plurality of candidate prediction motion vectors and the first motion vector, one of the plurality of candidate prediction motion vectors as the second motion vector, and determining a motion vector of the current block by using the first motion vector and the second motion vector.

公开(公告)号：US20230052330A1

公开(公告)日：2023-02-16

申请号：US17895416

申请日：2022-08-25

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jaehwan KIM ,  Youngo PARK ,  Jongseok LEE ,  Chaeeun LEE ,  Kwangpyo CHOI

IPC: G06T3/40

Abstract: Provided is an electronic apparatus configured to provide an image based on artificial intelligence (AI), the electronic apparatus including a processor configured to execute one or more instructions stored in the electronic apparatus to obtain a first image by AI-downscaling an original image by a downscaling neural network, obtain first image data by encoding the first image, based on a display apparatus not supporting an AI upscaling function, obtain a second image by decoding the first image data, obtain a third image by AI-upscaling the second image by an upscaling neural network, and provide, to the display apparatus, second image data obtained by encoding the third image.

公开(公告)号：US20220272352A1

公开(公告)日：2022-08-25

申请号：US17677414

申请日：2022-02-22

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Quockhanh DINH ,  Kwangpyo CHOI

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

Abstract: An image decoding method using artificial intelligence (AI), including obtaining feature data of a current optical flow and feature data of current differential data from a bitstream corresponding to a current image; obtaining the current optical flow by applying the feature data of the current optical flow to a neural-network-based first decoder; applying at least one of the feature data of the current optical flow and feature data of a previous optical flow to a first preprocessing neural network; obtain a first concatenation result by concatenating feature data obtained from the first preprocessing neural network with the feature data of the current differential data; obtaining the current differential data by applying the first concatenation result to a neural-network-based second decoder; and reconstructing the current image using the current differential data and a current predicted image generated from a previous reconstructed image based on the current optical flow.