公开(公告)号：US12175678B2

公开(公告)日：2024-12-24

申请号：US17749602

申请日：2022-05-20

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hanul Shin ,  Soomin Kang ,  Jaeyeon Park ,  Youngchan Song ,  Iljun Ahn ,  Tammy Lee

IPC: G06T7/12 ,  G06T5/50 ,  G06V10/44 ,  G06V10/54

Abstract: An image processing apparatus, including a memory configured to store one or more instructions; and at least one processor configured to execute the one or more instructions to: based on a first image and a probability model, optimize an estimated pixel value and estimated gradient values of each pixel of an original image corresponding to the first image, obtain an estimated original image based on the optimized estimated pixel value of the each pixel of the original image, obtain a decontour map based on the optimized estimated pixel value and the estimated gradient values of the each pixel of the original image, and generate a second image by combining the first image with the estimated original image based on the decontour map.

公开(公告)号：US12230008B2

公开(公告)日：2025-02-18

申请号：US17894685

申请日：2022-08-24

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jaeyeon Park ,  Iijun Ahn ,  Soomin Kang ,  Hanul Shin ,  Tammy Lee

IPC: G06K9/00 ,  G06T3/40 ,  G06V10/74 ,  G06V10/82

Abstract: An image processing apparatus, including a processor configured to execute instructions stored in a memory to: obtain characteristic information of a first image, divide the characteristic information into a plurality of groups, input each group into a respective layer of a plurality of layers included in a convolutional neural network and perform a convolution operation using one or more kernels to obtain a plurality of pieces of output information, generate an attention map including weight information corresponding to each pixel included in the first image, based on the plurality of pieces of output information, generate a spatially variant kernel including a kernel corresponding to the each pixel, based on the attention map and a spatial kernel including weight information according to a position relationship between the each pixel and a neighboring pixel, and generate a second image by applying the spatially variant kernel to the first image.

公开(公告)号：US20230360382A1

公开(公告)日：2023-11-09

申请号：US18136614

申请日：2023-04-19

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Soomin KANG ,  Youngchan Song ,  Tammy Lee ,  Jaeyeon Park ,  Hanul Shin ,  Iljun Ahn

IPC: G06V10/82 ,  G06V10/77 ,  G06V10/774 ,  G06T5/00 ,  G06T5/50 ,  G06F16/532

CPC classification number: G06V10/82 ,  G06V10/7715 ,  G06V10/774 ,  G06T5/002 ,  G06T5/50 ,  G06F16/532 ,  G06T2207/20192 ,  G06T2207/20021 ,  G06T2207/20084 ,  G06T2207/20081

Abstract: An image processing apparatus for processing an image by using one neural network, includes: a memory storing one instruction; and one processor configured to execute the one instruction to: obtain first feature data, based on a first image, obtain pieces of second feature data corresponding to first areas of the first image by performing first image processing on the first feature data, the first areas comprising a first number of pixels, obtain third feature data, based on the first image, obtain pieces of fourth feature data corresponding to second areas of the first image, by performing second image processing on the third feature data, the second areas comprising a second number of pixels that is greater than the first number, and generate a second image, based on the pieces of second feature data and the pieces of fourth feature data.

公开(公告)号：US12182981B2

公开(公告)日：2024-12-31

申请号：US17687227

申请日：2022-03-04

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hanul Shin ,  Soomin Kang ,  Iljun Ahn ,  Youngchan Song ,  Tammy Lee

IPC: G06T7/00

Abstract: An image processing apparatus and a method of operating the same are provided. The method includes: a memory storing one or more instructions; and a processor configured to execute the one or more instructions stored in the memory to obtain first frequency coefficient information by converting a first image into a frequency domain in units of blocks having a preset size, obtain correlation information indicating a correlation between at least one block of the first frequency coefficient information and a first kernel, generate a weight corresponding to the first frequency coefficient information based on the correlation information, generate second frequency coefficient information by rearranging coefficients included in the first frequency coefficient information, wherein the one or more of the coefficients having a same frequency is arranged into a same group, and obtain quality information of the first image based on the weight and the second frequency coefficient information.

公开(公告)号：US12086953B2

公开(公告)日：2024-09-10

申请号：US17687162

申请日：2022-03-04

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Iljun Ahn ,  Soomin Kang ,  Hanul Shin ,  Tammy Lee

IPC: G06T3/4046

CPC classification number: G06T3/4046 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: An image processing device, including a memory configured to store one or more instructions; and a processor configured to execute the one or more instructions stored in the memory to: obtain kernel coefficient information corresponding to each pixel of a plurality of pixels included in a first image, using a convolution neural network including one or more convolution layers, generate a spatially variant kernel including a kernel corresponding to the each pixel, based on a gradient kernel set including a plurality of gradient kernels corresponding to one or more gradient characteristics of the plurality of pixels, and the kernel coefficient information, and generate a second image, by applying the kernel included in the spatially variant kernel to a region centered on the each pixel, and filtering the first image.

公开(公告)号：US20220284545A1

公开(公告)日：2022-09-08

申请号：US17687162

申请日：2022-03-04

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Iljun AHN ,  Soomin Kang ,  Hanul Shin ,  Tammy Lee

IPC: G06T3/40

Abstract: An image processing device, including a memory configured to store one or more instructions; and a processor configured to execute the one or more instructions stored in the memory to: obtain kernel coefficient information corresponding to each pixel of a plurality of pixels included in a first image, using a convolution neural network including one or more convolution layers, generate a spatially variant kernel including a kernel corresponding to the each pixel, based on a gradient kernel set including a plurality of gradient kernels corresponding to one or more gradient characteristics of the plurality of pixels, and the kernel coefficient information, and generate a second image, by applying the kernel included in the spatially variant kernel to a region centered on the each pixel, and filtering the first image.