公开(公告)号：US20220245767A1

公开(公告)日：2022-08-04

申请号：US17573010

申请日：2022-01-11

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Bongjoe KIM ,  Kyuha CHOI ,  Seungho PARK ,  Sangjo LEE

IPC: G06T5/00 ,  G06T7/00 ,  G06T5/50

Abstract: An image processing apparatus includes: a memory storing one or more instructions; and a processor by executing the one or more instructions stored in the memory is configured to: extract a first image feature from a first image; search for, based on a transmission characteristic of the first image and the first image feature, a first cluster corresponding to the first image from among a plurality of clusters stored in the image processing apparatus, each cluster including a representative image feature and a representative image quality parameter; perform image quality processing on the first image based on a first representative image quality parameter in the first cluster; obtain, based on the first image that has undergone the image quality processing, a first update parameter obtained by updating the first representative image quality parameter; and update the plurality of clusters based on the first update parameter.

公开(公告)号：US20240144438A1

公开(公告)日：2024-05-02

申请号：US18541561

申请日：2023-12-15

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jaesung PARK ,  Younghoon JEONG ,  Jongho KIM ,  Kyuha CHOI ,  Youngsu MOON

IPC: G06T5/50 ,  G06T3/40 ,  G06T5/70 ,  G06T7/13 ,  G06T7/50 ,  G06V10/46 ,  G06V10/54

CPC classification number: G06T5/50 ,  G06T3/40 ,  G06T5/70 ,  G06T7/13 ,  G06T7/50 ,  G06V10/46 ,  G06V10/54 ,  G06T2207/10024 ,  G06T2207/20221

Abstract: A display apparatus is disclosed. The display apparatus includes: a display; a memory storing at least one instruction; and one or more processors connected to the display and the memory to control the display apparatus, wherein the one or more processors are configured to: pre-process an image; obtain an edge image by identifying a contour corresponding to each of a plurality of objects included in the pre-processed image; perform image processing to adjust at least one of a thickness or a color of each of the plurality of contours included in the edge image; obtain an output image by overlaying or blending the edge image subjected to image processing on or with the pre-processed image; and display the output image through the display.

公开(公告)号：US20250045881A1

公开(公告)日：2025-02-06

申请号：US18923346

申请日：2024-10-22

Applicant: SAMSUNG ELECTRONICS CO., LTD. ,  SEOUL NATIONAL UNIVERSITY R&DB FOUNDATION

Inventor： Hyunseung LEE ,  Seokhee LEE ,  Kyuha CHOI ,  Youngsu MOON ,  Karam PARK ,  Younghoon JEONG ,  Namik CHO ,  Sunwoo CHO

IPC: G06T5/60 ,  G06T3/4046 ,  G06T3/4053 ,  G06T5/20

Abstract: An image processing apparatus, including: at least one processor; and a memory configured to store one or more instructions which, when executed by the at least one processor, cause the image processing apparatus to: obtain a neural network model for performing image quality processing on an input image; calculate a plurality of gradients by partially differentiating weights of the neural network model with respect to a loss of the neural network model, by applying training data corresponding to the input image to the neural network model; remove at least one gradient from among the plurality of gradients by applying a gradient mask including gradient pruning information to the plurality of gradients; train the neural network model by updating the weights of the neural network model based on one or more remaining gradients from among the plurality of gradients; and obtain a quality-processed output image based on the input image, using the trained neural network model

公开(公告)号：US20240378761A1

公开(公告)日：2024-11-14

申请号：US18781478

申请日：2024-07-23

Applicant: SAMSUNG ELECTRONICS CO.,LTD.

Inventor： Daesung CHO ,  Daeeun KIM ,  Bongjoe KIM ,  Taejun PARK ,  Sangjo LEE ,  Kyuha CHOI

IPC: G06T9/00 ,  G06N3/045 ,  G06T3/4046 ,  G06T7/00

Abstract: An artificial intelligence (AI) encoding apparatus includes at least one processor configured to: determine a downscaling target, based on a target resolution for a first image, obtain the first image by AI-downscaling an original image using an AI-downscaling neural network corresponding to the downscaling target, generate image data by encoding the first image, select AI-upscaling neural network set identification information, based on the target resolution of the first image, characteristic information of the original image, and a target detail intensity, generate AI data including the target resolution of the first image, bit depth information of the first image, the AI-upscaling neural network set identification information, and encoding control information, and generate AI encoding data including the image data and the AI data; and a communication interface configured to transmit the AI encoding data to an AI decoding apparatus, wherein the AI data includes information about an AI-upscaling neural network corresponding to the AI-downscaling neural network.

公开(公告)号：US20220414828A1

公开(公告)日：2022-12-29

申请号：US17902775

申请日：2022-09-02

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Kyuha CHOI ,  Bongjoe KIM ,  Daeeun KIM ,  Taejun PARK

IPC: G06T3/40 ,  H04N19/33

Abstract: An electronic apparatus includes a memory configured to store a downscaling network of a first artificial intelligene model, a communication interface comprising communication circuitry, and a processor connected to the memory and the communication interface and configured to control the electronic apparatus, wherein the processor is configured to: obtain an output image in which an input image is downscaled by inputting the input image the downscaling network, control the communication interface to transmit the output image to another electronic apparatus, and wherein the first artificial intelligene model is configured to be learned based on: a sample image, a first intermediate image obtained by inputting the sample image to the downscaling network, a first final image obtained by inputting the first intermediate image to an upscaling network of the first artificial intelligene model, a second intermediate image in which the sample image is downscaled by a legacy scaler, and a second final image in which the first intermediate image is upscaled by the legacy scaler.

公开(公告)号：US20220180568A1

公开(公告)日：2022-06-09

申请号：US17522579

申请日：2021-11-09

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Daesung CHO ,  Daeeun KIM ,  Bongjoe KIM ,  Taejun PARK ,  Sangjo LEE ,  Kyuha CHOI

IPC: G06T9/00 ,  G06T3/40 ,  G06T7/00 ,  G06N3/04

Abstract: An artificial intelligence (AI) encoding apparatus includes at least one processor configured to: determine a downscaling target, based on a target resolution for a first image, obtain the first image by AI-downscaling an original image using an AI-downscaling neural network corresponding to the downscaling target, generate image data by encoding the first image, select AI-upscaling neural network set identification information, based on the target resolution of the first image, characteristic information of the original image, and a target detail intensity, generate AI data including the target resolution of the first image, bit depth information of the first image, the AI-upscaling neural network set identification information, and encoding control information, and generate AI encoding data including the image data and the AI data; and a communication interface configured to transmit the AI encoding data to an AI decoding apparatus, wherein the AI data includes information about an AI-upscaling neural network corresponding to the AI-downscaling neural network.

公开(公告)号：US20220109900A1

公开(公告)日：2022-04-07

申请号：US17419149

申请日：2019-11-01

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hyungyeol LEE ,  Jeongdon KANG ,  Changwon NAM ,  Bonghoon PARK ,  Kyuha CHOI

IPC: H04N21/2668 ,  H04N21/81 ,  H04N21/234

Abstract: The present disclosure relates to a system for intermediating a virtual image, the system including: a communicator configured to receive, from a first device, user information and information about broadcast content into which a virtual image is to be inserted and receive virtual images from a second device; a memory storing one or more instructions; and a processor configured to execute the one or more instructions stored in the memory to: determine, based on the user information and the information about the broadcast content, one or more virtual images that are insertable into the broadcast content from among the virtual images; and control the determined one or more virtual images to be transmitted to the first device.

公开(公告)号：US20220084167A1

公开(公告)日：2022-03-17

申请号：US17464119

申请日：2021-09-01

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Kyuha CHOI ,  Bongjoe KIM ,  Daeeun KIM ,  Taejun PARK

IPC: G06T3/40 ,  H04N19/33

Abstract: An electronic apparatus is dislcosed. The electronic apparatus includes: a memory configured to store a downscaling network of a first artificial intelligene model, a communication interface comprising communication circuitry, and a processor connected to the memory and the communication interface and configured to control the electronic apparatus, wherein the processor is configured to: obtain an output image in which an input image is downscaled by inputting the input image the downscaling network, control the communication interface to trasnmit the output image to another electronic apparatus, and wherein the first artificial intelligene model is configured to be learned based on: a sample image, a first intermediate image obtained by inputting the sample image to the downscaling network, a first final image obtained by inputting the first intermediate image to an upscaling network of the first artificial intelligene model, a second intermediate image in which the sample image is downscaled by a legacy scaler, and a second final image in which the first intermediate image is upscaled by the legacy scaler.