公开(公告)号：US20150131718A1

公开(公告)日：2015-05-14

申请号：US14600953

申请日：2015-01-20

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jung-hye MIN ,  Tammy LEE ,  Il-koo KIM

IPC: H04N19/139 ,  H04N19/182 ,  H04N19/159 ,  H04N19/86 ,  H04N19/117

CPC classification number: H04N19/86 ,  H04N19/105 ,  H04N19/117 ,  H04N19/119 ,  H04N19/122 ,  H04N19/139 ,  H04N19/157 ,  H04N19/159 ,  H04N19/182 ,  H04N19/395 ,  H04N19/50 ,  H04N19/52 ,  H04N19/593 ,  H04N19/61 ,  H04N19/80 ,  H04N19/82 ,  H04N19/96

Abstract: A method and apparatus for encoding video by using deblocking filtering, and a method and apparatus for decoding video by using deblocking filtering are provided. The method of encoding video includes: splitting a picture into a maximum coding unit; determining coding units of coded depths and encoding modes for the coding units of the maximum coding unit by prediction encoding the coding units of the maximum coding unit based on at least one prediction unit and transforming the coding units based on at least one transformation unit, wherein the maximum coding unit is hierarchically split into the coding units as a depth deepens, and the coded depths are depths where the maximum coding unit is encoded in the coding units; and performing deblocking filtering on video data being inversely transformed into a spatial domain in the coding units, in consideration of the encoding modes.

Abstract translation: 提供了一种通过使用解块滤波对视频进行编码的方法和装置，以及通过使用去块滤波来解码视频的方法和装置。 视频编码方法包括：将图像分割为最大编码单位; 基于至少一个预测单元对最大编码单元的编码单位进行预测编码，基于至少一个变换单位对编码单位进行变换，确定最大编码单位的编码单位的编码深度的编码单位和编码模式，其中， 最大编码单位在深度加深的情况下被分层分割为编码单元，编码深度是最大编码单元在编码单元中被编码的深度; 并且考虑到编码模式，对编码单元中的空间域进行逆变换的视频数据进行去块滤波。

公开(公告)号：US20140286585A1

公开(公告)日：2014-09-25

申请号：US14299131

申请日：2014-06-09

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Tammy LEE ,  Woo-jin HAN ,  Jianle CHEN ,  Hae-kyung JUNG

IPC: G06T9/00

CPC classification number: H04N19/625 ,  G06T9/00 ,  H04N19/107 ,  H04N19/119 ,  H04N19/122 ,  H04N19/169 ,  H04N19/176 ,  H04N19/61 ,  H04N19/70 ,  H04N19/96

Abstract: An image decoding method including determining coding units having a hierarchical structure for decoding an image using split information of a coding unit, determining at least one prediction unit for predicting a coding unit among the coding units using information about a partition type, determining at least one transformation unit for inversely transforming the coding unit using split information of the at least one transformation unit, wherein the split information of a coding unit, the information about a partition type and the information about a depth of the at least one transformation unit are parsed from a bitstream, parsing from the bitstream transformation coefficients generated by transformation according to the at least one transformation unit generated by dividing the coding unit, reconstructing residual of the at least one transformation unit by performing inverse quantization and inverse transformation on the parsed transformation coefficients, and performing intra prediction or inter prediction on the prediction unit to generate a predictor, and reconstructs the image based on the residual and the predictor.

Abstract translation: 一种图像解码方法，包括确定具有用于使用编码单元的分割信息对图像进行解码的分层结构的编码单元，使用关于分区类型的信息确定用于在编码单元中预测编码单元的至少一个预测单元，确定至少一个 变换单元，用于使用所述至少一个变换单元的分割信息对所述编码单元进行逆变换，其中编码单元的分割信息，关于分割类型的信息和关于所述至少一个变换单元的深度的信息被从 比特流，根据通过对编码单元进行分割而生成的至少一个变换单元，通过变换生成的位流变换系数进行解析，对解析变换系数进行逆量化和逆变换，对至少一个变换单位的残差进行重构;以及 执行内部预处理 对预测单元进行预测或帧间预测以生成预测器，并且基于残差和预测器来重建图像。

公开(公告)号：US20140286411A1

公开(公告)日：2014-09-25

申请号：US14219397

申请日：2014-03-19

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Seung-soo JEONG ,  Chan-yul KIM ,  Tammy LEE ,  Young-ho MOON ,  Jeong-hoon PARK

IPC: H04N19/30 ,  H04N19/593

CPC classification number: H04N19/593 ,  H04N19/33

Abstract: Provided are scalable video encoding and decoding methods. The scalable video encoding method includes: obtaining a peripheral pixel of an enhancement block based on a peripheral pixel of a base layer block corresponding to the enhancement layer block to be prediction-encoded, and performing intra prediction on the enhancement layer block by using at least one of a peripheral pixel of the enhancement layer block that is encoded before the enhancement layer block and then restored and a peripheral pixel of the enhancement layer block that is obtained based on a peripheral pixel of the base layer block.

Abstract translation: 提供了可扩展的视频编码和解码方法。 可扩展视频编码方法包括：基于与要进行预测编码的增强层块相对应的基本层块的外围像素获得增强块的外围像素，并且至少使用增强层块进行帧内预测 所述增强层块的周边像素之一，其在所述增强层块之前被编码，然后被恢复，以及基于所述基本层块的外围像素获得的所述增强层块的外围像素。

公开(公告)号：US20140198996A1

公开(公告)日：2014-07-17

申请号：US14218494

申请日：2014-03-18

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Elena ALSHINA ,  Alexander ALSHIN ,  Nikolay SHLYAKHOV ,  Byeong-doo CHOI ,  Yoon-mi HONG ,  Woo-jin HAN ,  Tammy LEE

IPC: G06T3/40

CPC classification number: G06T3/4007 ,  G06F17/175 ,  H04N7/014 ,  H04N19/117 ,  H04N19/182 ,  H04N19/30 ,  H04N19/48 ,  H04N19/523 ,  H04N19/59 ,  H04N19/80

Abstract: Provided are a method and apparatus for interpolating an image. The method includes: selecting a first filter, from among a plurality of different filters, for interpolating between pixel values of integer pixel units, according to an interpolation location; and generating at least one pixel value of at least one fractional pixel unit by interpolating between the pixel values of the integer pixel units by using the selected first filter.

Abstract translation: 提供了一种用于内插图像的方法和装置。 该方法包括：根据插值位置，从多个不同滤波器中选择第一滤波器，用于在整数像素单元的像素值之间进行内插; 以及通过使用所选择的第一滤波器在整数像素单元的像素值之间进行内插来生成至少一个分数像素单元的至少一个像素值。

公开(公告)号：US20130142265A1

公开(公告)日：2013-06-06

申请号：US13755530

申请日：2013-01-31

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Tammy LEE ,  Woo-jin HAN

IPC: H04N7/26

CPC classification number: H04N19/521 ,  H04N19/105 ,  H04N19/137 ,  H04N19/14 ,  H04N19/159 ,  H04N19/176 ,  H04N19/182 ,  H04N19/51 ,  H04N19/513 ,  H04N19/52 ,  H04N19/593 ,  H04N19/61

Abstract: Provided are a method and apparatus for estimating a motion vector using a plurality of motion vector predictors, an encoder, a decoder, and a decoding method. The method includes calculating spatial similarities between the current block and the plurality of neighboring partitions around the current block, selecting at least one of the neighboring partitions based on the calculated spatial similarities, and estimating a motion vector of the selected partition as the motion vector of the current block.

公开(公告)号：US20130128973A1

公开(公告)日：2013-05-23

申请号：US13746297

申请日：2013-01-21

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Woo-jin HAN ,  Sang-rae LEE ,  Tammy LEE ,  Jung-hye MIN

IPC: H04N7/26

CPC classification number: H04N19/154 ,  H04N19/105 ,  H04N19/124 ,  H04N19/172 ,  H04N19/176 ,  H04N19/177 ,  H04N19/43 ,  H04N19/46 ,  H04N19/58 ,  H04N19/61

Abstract: A method and apparatus for encoding and decoding an image by performing motion prediction and compensation on pictures in a group of pictures by selectively using a high-quality key picture that is previously encoded and restored, and a second picture that is previously encoded and restored. The method of encoding an image improves the prediction efficiency of an image by storing a key picture, which is encoded and restored to a high quality by reducing a loss caused by a quantization error using a small quantization coefficient, in a first storage unit and storing a previously encoded and restored second picture in a second storage unit, and then performing motion prediction and compensation by selectively using the key picture stored in the first storage unit and the second picture stored in the second storage unit while encoding a next picture in a group of pictures.

公开(公告)号：US20130058415A1

公开(公告)日：2013-03-07

申请号：US13670018

申请日：2012-11-06

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Tammy LEE ,  Woo-jin HAN ,  Kyo-hyuk LEE

IPC: H04N7/32

CPC classification number: H04N19/139 ,  H04N19/105 ,  H04N19/117 ,  H04N19/124 ,  H04N19/147 ,  H04N19/159 ,  H04N19/176 ,  H04N19/184 ,  H04N19/51 ,  H04N19/513 ,  H04N19/52 ,  H04N19/61 ,  H04N19/70 ,  H04N19/865 ,  H04N19/96

Abstract: Provided are methods and apparatuses for encoding and decoding a motion vector. The method of encoding the motion vector includes: selecting, as a mode of encoding information about a motion vector predictor of the current block, a first mode in which information indicating the motion vector predictor from among at least one motion vector predictor is encoded or a second mode in which information indicating generation of the motion vector predictor based on blocks or pixels included in a previously encoded area adjacent to the current block is encoded; determining the motion vector predictor of the current block according to the selected mode and encoding the information about the motion vector predictor of the current block; and encoding a difference vector between the motion vector of the current block and the motion vector predictor of the current block.

公开(公告)号：US20230360169A1

公开(公告)日：2023-11-09

申请号：US18135992

申请日：2023-04-18

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jaeyeon PARK ,  Iljun AHN ,  Tammy LEE ,  Soomin KANG ,  Youngchan SONG ,  Hanul SHIN

IPC: G06T3/40 ,  G06T5/50

CPC classification number: G06T3/40 ,  G06T5/50 ,  G06T2207/20016

Abstract: An image processing apparatus for performing an image by using one or more neural networks may include a memory storing one or more instructions and at least one processor configured to execute the one or more instructions stored in the memory to obtain first feature information of a first image, generate an intermediate output image for the first image by performing first image processing on the first feature information, generate an attention map, based on the first image and the intermediate output image, obtain second feature information by performing second image processing on the first feature information, obtain fourth feature information by performing third image processing on third feature information extracted during the first image processing, and generate a second image having a higher quality than the first image, based on the attention map, the second feature information, and the fourth feature information.

公开(公告)号：US20230169752A1

公开(公告)日：2023-06-01

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: G06V10/74 ,  G06V10/82 ,  G06T3/40

CPC classification number: G06V10/761 ,  G06V10/82 ,  G06T3/40

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：US20230071417A1

公开(公告)日：2023-03-09

申请号：US17987574

申请日：2022-11-15

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Iljun AHN ,  Tammy LEE ,  Soomin KANG ,  Jaeyeon PARK

IPC: G06T5/00 ,  G06T5/50

Abstract: An image processing apparatus includes a memory storing at least one instruction; and a processor configured to execute the at least one instruction to use at least one neural network to: extract n pieces of first feature information from a first image, based on locations of pixels included in the first image, wherein n is a positive integer, generate n pieces of second feature information by performing a convolution operation between each of the n pieces of the first feature information and each of n kernels, and generate, based on the n pieces of the second feature information, a second image from which compression artifacts included in the first image are removed.