-
公开(公告)号：EP4365822A1
公开(公告)日：2024-05-08
申请号：EP22901634.0
申请日：2022-11-17
发明人： AHN, Iljun , KANG, Soomin , PARK, Jaeyeon , SONG, Youngchan , SHIN, Hanul , LEE, Tammy
CPC分类号： G06V10/74 , G06T5/60 , G06T2207/2008120130101 , G06T2207/2008420130101 , G06N3/0464 , G06N3/08
摘要： An image processing apparatus for processing an image by using one or more convolution neural networks, according to an embodiment, may comprise a memory that stores one or more instructions, and at least one processor, by executing the one or more instructions stored in the memory: acquires first feature data by performing a convolution operation between input data, which has been acquired from a first image, and a first kernel; segments, into first groups, a plurality of channels included in the first feature data; acquires pieces of second feature data by performing a convolution operation between pieces of the first feature data respectively corresponding to the first groups and second kernels respectively corresponding to the first groups; acquires pieces of shuffling data by shuffling the pieces of second feature data; acquires output data by performing a convolution operation between data obtained by summing channels included in the pieces of shuffling data and a third kernel; and generates a second image on the basis of the output data.
-
公开(公告)号：EP4276744A1
公开(公告)日：2023-11-15
申请号：EP22763484.7
申请日：2022-02-11
发明人： SHIN, Hanul , KANG, Soomin , AHN, Iljun , SONG, Youngchan , LEE, Tammy
摘要： 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：EP4083874A1
公开(公告)日：2022-11-02
申请号：EP22705003.6
申请日：2022-02-11
发明人： AHN, Iljun , KANG, Soomin , SHIN, Hanul , LEE, Tammy
摘要： 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：EP4369282A1
公开(公告)日：2024-05-15
申请号：EP22864869.7
申请日：2022-07-22
发明人： AHN, Iljun , KANG, Soomin , SHIN, Hanul , LEE, Tammy
摘要： An image processing apparatus may include: a memory storing one or more instructions; and a processor configured to execute the one or more instructions stored in the memory, wherein the processor executes the one or more instructions to use one or more convolutional neural networks to: determine first parameters, based on position information of first pixels included in a first region of a first image and position information of samples of the first image; obtain sample values of the samples by applying the first parameters to pixel values of the first pixels; obtain feature information corresponding to the first region by performing a convolution operation between the sample values and a kernel of the one or more convolutional neural networks; and generate a second image, based on the feature information.
-
公开(公告)号：EP4187482A1
公开(公告)日：2023-05-31
申请号：EP21869623.5
申请日：2021-09-08
发明人： LEE, Tammy , KANG, Soomin , PARK, Jaeyeon , SONG, Youngchan , AHN, Iljun
摘要： An image processing apparatus is provided, the image processing 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 similarity information, based on a difference between each of pixels included in a first image and an adjacent pixel of each of the pixels, based on the similarity information, determine weight information, obtain first feature information through a convolution operation between the first image and a first kernel, obtain second feature information by applying the weight information to the first feature information, and based on the second feature information, generate a second image.
-
公开(公告)号：EP4365827A1
公开(公告)日：2024-05-08
申请号：EP22895779.1
申请日：2022-07-14
发明人： PARK, Jaeyeon , AHN, Iljun , KANG, Soomin , SHIN, Hanul , LEE, Tammy
CPC分类号： G06V10/454 , G06V10/82
摘要： 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：EP4318384A1
公开(公告)日：2024-02-07
申请号：EP22804879.9
申请日：2022-05-06
发明人： SHIN, Hanul , KANG, Soomin , PARK, Jaeyeon , SONG, Youngchan , AHN, Iljun , LEE, Tammy
摘要： 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.
-
-
-
-
-
-
搜索结果
7 条记录 (耗时 0.011 秒)
