-
公开(公告)号:US20230069072A1
公开(公告)日:2023-03-02
申请号:US17888170
申请日:2022-08-15
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Iljun AHN , Soomin KANG , Hanul SHIN , Tammy LEE
Abstract: 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:US20220076375A1
公开(公告)日:2022-03-10
申请号:US17527732
申请日:2021-11-16
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Cheon LEE , Donghyun KIM , Yongsup PARK , Jaeyeon PARK , lljun AHN , Hyunseung LEE , Taegyoung AHN , Youngsu MOON , Tammy LEE
Abstract: An image processing apparatus applies an image to a first learning network model to optimize the edges of the image, applies the image to a second learning network model to optimize the texture of the image, and applies a first weight to the first image and a second weight to the second image based on information on the edge areas and the texture areas of the image to acquire an output image.
-
公开(公告)号:US20220012897A1
公开(公告)日:2022-01-13
申请号:US17294000
申请日:2019-11-11
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Dubok PARK , Kwanghyun WON , Tammy LEE
Abstract: Provided is an image processing apparatus including a memory storing one or more instructions, and a processor executing the one or more instructions stored in the memory, wherein the processor retargets a current frame image, based on a first scale factor for a previous frame image, a second scale factor for the current frame image, and a weight determined based on previous frame image data and current frame image data.
-
公开(公告)号:US20210183015A1
公开(公告)日:2021-06-17
申请号:US17271328
申请日:2019-09-11
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Iljun AHN , Yongsup PARK , Jaeyeon PARK , Minsu CHEON , Tammy LEE
Abstract: Provided is an 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, wherein the processor is further configured to execute the one or more instructions to generate a second image by performing a deconvolution operation on a first image and a kernel comprising one or more weights, set values of the one or more weights based on the second image, and adjust the values of the one or more weights based on positions of the one or more weights in the kernel.
-
105.
公开(公告)号:US20200045335A1
公开(公告)日:2020-02-06
申请号:US16598031
申请日:2019-10-10
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Tammy LEE , Woo-jin HAN
IPC: H04N19/56 , H04N19/46 , H04N19/503 , H04N19/51 , H04N19/52 , H04N19/61 , H04N19/172 , H04N19/176 , H04N19/513
Abstract: A method and apparatus for encoding and decoding a motion vector of a current block. The method of encoding including: generating information about the motion vector based on a motion vector of a current block and a motion vector predictor of the current block by estimating the motion vector and determining a first motion vector predictor candidate from among a plurality of motion vector predictor candidates as the motion vector predictor based on a result of the estimating; and generating a virtual motion vector by using a second motion vector predictor candidate and the information about the motion vector, generating vector differences between the virtual motion vector and the plurality of motion vector predictor candidates, comparing the vector differences with the information about the motion vector, and selectively excluding the second motion vector predictor candidate according to the comparing.
-
公开(公告)号:US20190364269A1
公开(公告)日:2019-11-28
申请号:US16538235
申请日:2019-08-12
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Chang-Hyun LEE , Tammy LEE , Jianle CHEN , Dae-sung CHO , Woo-jin HAN , Il-koo KIM
IPC: H04N19/103 , H04N19/61 , H04N19/46 , H04N19/176 , H04N19/57 , H04N19/119
Abstract: A video encoding method and apparatus and a video decoding method and apparatus are provided. The video encoding method includes: prediction encoding in units of a coding unit as a data unit for encoding a picture, by using partitions determined based on a first partition mode and a partition level, so as to select a partition for outputting an encoding result from among the determined partitions; and encoding and outputting partition information representing a first partition mode and a partition level of the selected partition. The first partition mode represents a shape and directionality of a partition as a data unit for performing the prediction encoding on the coding unit, and the partition level represents a degree to which the coding unit is split into partitions for detailed motion prediction.
-
107.
公开(公告)号:US20180338155A1
公开(公告)日:2018-11-22
申请号:US16047567
申请日:2018-07-27
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Tammy LEE , Woo-jin HAN
IPC: H04N19/56 , H04N19/513 , H04N19/176 , H04N19/172
CPC classification number: H04N19/56 , H04N19/172 , H04N19/176 , H04N19/184 , H04N19/46 , H04N19/503 , H04N19/51 , H04N19/513 , H04N19/52 , H04N19/61
Abstract: A method and apparatus for encoding and decoding a motion vector of a current block. The method of encoding including: generating information about the motion vector based on a motion vector of a current block and a motion vector predictor of the current block by estimating the motion vector and determining a first motion vector predictor candidate from among a plurality of motion vector predictor candidates as the motion vector predictor based on a result of the estimating; and generating a virtual motion vector by using a second motion vector predictor candidate and the information about the motion vector, generating vector differences between the virtual motion vector and the plurality of motion vector predictor candidates, comparing the vector differences with the information about the motion vector, and selectively excluding the second motion vector predictor candidate according to the comparing.
-
公开(公告)号:US20180205950A1
公开(公告)日:2018-07-19
申请号:US15918347
申请日:2018-03-12
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Min-su CHEON , Woo-jin HAN , Hae-kyung JUNG , Il-koo KIM , Tammy LEE , Jianle CHEN
IPC: H04N19/122 , H04N19/119 , H04N19/124 , H04N19/13 , H04N19/159
CPC classification number: H04N19/122 , G06T9/00 , H04N19/107 , H04N19/119 , H04N19/124 , H04N19/13 , H04N19/147 , H04N19/159 , H04N19/176 , H04N19/182 , H04N19/30 , H04N19/50 , H04N19/503 , H04N19/60 , H04N19/61 , H04N19/91 , H04N19/96
Abstract: A method of decoding an image in which wherein, when a prediction mode is an inter prediction mode, not an intra prediction mode, a size of at least one prediction unit in the coding unit is determined independently from a size of at least one transformation unit in the coding unit.
-
109.
公开(公告)号:US20180160121A1
公开(公告)日:2018-06-07
申请号:US15874347
申请日:2018-01-18
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Tammy LEE , Woo-Jin HAN , Il-Koo KIM
IPC: H04N19/146 , H04N19/86 , H04N19/172 , H04N19/119 , H04N19/82
CPC classification number: H04N19/146 , H04N19/105 , H04N19/109 , H04N19/117 , H04N19/119 , H04N19/124 , H04N19/13 , H04N19/14 , H04N19/157 , H04N19/159 , H04N19/172 , H04N19/182 , H04N19/184 , H04N19/51 , H04N19/61 , H04N19/82 , H04N19/86 , H04N19/865
Abstract: A method of decoding video, the method including receiving and parsing a bitstream which includes encoded video; extracting encoded image data relating to a current picture, which image data is assigned to at least one maximum coding unit, information relating to a coded depth and an encoding mode for each of the at least one maximum coding unit, and filter coefficient information for performing loop filtering on the current picture, from the bitstream; decoding the encoded image data in units of the at least one maximum coding unit, based on the information relating to the coded depth and the encoding mode for each of the at least one maximum coding unit; and performing deblocking on the decoded image data relating to the current picture, and performing loop filtering on the deblocked data, based on continuous one-dimensional (1D) filtering.
-
公开(公告)号:US20170295381A1
公开(公告)日:2017-10-12
申请号:US15625640
申请日:2017-06-16
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Woong-Il CHOI , Woo-jin HAN , Tammy LEE , Sun-il LEE
IPC: H04N19/91 , H04N19/176 , H04N19/124 , H04N19/44 , H04N19/61 , H04N19/70 , H04N19/30
CPC classification number: H04N19/91 , H04N19/124 , H04N19/172 , H04N19/176 , H04N19/30 , H04N19/44 , H04N19/61 , H04N19/70
Abstract: Entropy encoding and entropy decoding of image data are respectively performed whereby context modeling is performed on a context unit of blocks of the image data based on a context model of a previously encoded or decoded block.
-
-
-
-
-
-
-
-
-