公开(公告)号：US20230132843A1

公开(公告)日：2023-05-04

申请号：US18087577

申请日：2022-12-22

申请人： Electronics and Telecommunications Research Institute ,  CHIPS&MEDIA, INC

发明人： Sung Chang LIM ,  Jung Won KANG ,  Ha Hyun LEE ,  Jin Ho LEE ,  Hui Yong KIM ,  Dae Yeon KIM ,  Wook Je JEONG ,  Hyun Gyu KIM

IPC分类号： H04N19/13 ,  H04N19/176 ,  H04N19/70

摘要： An image decoding method is disclosed in the present specification. A method of decoding an image, the method may comprises determining whether to perform a context update for a first syntax element of a current block, updating, on the basis of the determination, a context for entropy decoding of the first syntax element and generating, on the basis of the updated context, a bin for the first syntax element, and wherein whether to perform the context update is determined on the basis of the number of pre-decoded predetermined syntax elements for the current block.

公开(公告)号：US20230128151A1

公开(公告)日：2023-04-27

申请号：US18086228

申请日：2022-12-21

申请人： Sun Patent Trust

发明人： Toshiyasu SUGIO ,  Takahiro NISHI ,  Youji SHIBAHARA ,  Kyoko TANIKAWA ,  Hisao SASAI ,  Toru MATSUNOBU

IPC分类号： H04N19/139 ,  H04N19/105 ,  H04N19/52 ,  H04N19/176 ,  H04N19/70 ,  H04N19/51 ,  H04N19/13 ,  H04N19/134 ,  H04N19/102 ,  H04N19/577

摘要： A method for transmitting a bitstream via a network is provided. The bitstream is for coding a current block and is generated by: deriving a first candidate from a first motion vector that has been used to code a first block; coding a first index identifying a reference picture to be used for coding the current block; deriving a second candidate having a second motion vector that includes a non-zero value, which is assigned to the reference picture; and coding a second index identifying a selected candidate to be used for coding the current block. The second motion vector is not derived by coding a block adjacent to the current block, and the non-zero value is assigned by offset values which include an OffsetX and an OffsetY and which are located in a picture header.

公开(公告)号：US20230125381A1

公开(公告)日：2023-04-27

申请号：US18146372

申请日：2022-12-24

申请人： HUAWEI TECHNOLOGIES CO., LTD.

发明人： Timofey Mikhailovich SOLOVYEV ,  Semih Esenlik ,  Jianle Chen ,  Anand Meher Kotra ,  Han Gao ,  Biao Wang ,  Roman Igorevich Chernyak ,  Alexander Alexandrovich Karabutov ,  Sergey Yurievich Ikonin

IPC分类号： H04N19/503 ,  H04N19/105 ,  H04N19/13 ,  H04N19/132 ,  H04N19/159 ,  H04N19/176

摘要： A prediction method for an image block comprising a first prediction sub-block and a second prediction sub-block, the prediction method comprising: parsing a first index from a bitstream, wherein the first index is used to obtain prediction information of the first prediction sub-block; parsing a second index from the bitstream; comparing the first index with the second index; adjusting the second index in the event that the second index is equal to or greater than the first index; and obtaining prediction information of the second prediction sub-block according to the adjusted second index.

公开(公告)号：US11638007B2

公开(公告)日：2023-04-25

申请号：US17446862

申请日：2021-09-03

申请人： Adobe Inc.

发明人： Viswanathan Swaminathan ,  Rashmi Mittal

IPC分类号： H04N19/13 ,  H04N19/94 ,  H04N19/176 ,  H04N19/196

摘要： Techniques are disclosed for the improvement of vector quantization (VQ) codebook generation. The improved codebooks may be used for compression in cloud-based video applications. VQ achieves compression by vectorizing input video streams, matching those vectors to codebook vector entries, and replacing them with indexes of the matched codebook vectors along with residual vectors to represent the difference between the input stream vector and the codebook vector. The combination of index and residual is generally smaller than the input stream vector which they collectively encode, thus providing compression. The improved codebook may be generated from training video streams by grouping together similar types of data (e.g., image data, motion data, control data) from the video stream to generate longer vectors having higher dimensions and greater structure. This improves the ability of VQ to remove redundancy and thus increase compression efficiency. Storage space is thus reduced and video transmission may be faster.

公开(公告)号：US11638006B2

公开(公告)日：2023-04-25

申请号：US17167866

申请日：2021-02-04

申请人： SAMSUNG ELECTRONICS CO., LTD.

发明人： Elena Alshina ,  Mikhail Mishurovskiy ,  Alexander Alshin

IPC分类号： H04N19/91 ,  H04N19/44 ,  H04N19/61 ,  H04N19/137 ,  H04N19/51 ,  H04N19/124 ,  H04N19/122 ,  H04N19/182 ,  H04N19/126 ,  H04N19/70 ,  H04N19/194 ,  H04N19/11 ,  H04N19/109 ,  H04N19/18 ,  H04N19/537 ,  H04N19/46 ,  H04N19/593 ,  H04N19/63 ,  H04N19/13 ,  H04N19/436 ,  H04N19/139 ,  H04N19/176 ,  H04N19/513 ,  H04N19/57

摘要： An image decoding method and apparatus according to an embodiment may extract, from a bitstream, a quantization coefficient generated through core transformation, secondary transformation, and quantization; generate an inverse-quantization coefficient by performing inverse quantization on the quantization coefficient; generate a secondary inverse-transformation coefficient by performing secondary inverse-transformation on a low frequency component of the inverse-quantization coefficient, the secondary inverse-transformation corresponding to the secondary transformation; and perform core inverse-transformation on the secondary inverse-transformation coefficient, the core inverse-transformation corresponding to the core transformation.

公开(公告)号：US11616989B2

公开(公告)日：2023-03-28

申请号：US17074319

申请日：2020-10-19

申请人： LG ELECTRONICS INC.

发明人： Jae Hyun Lim ,  Seung Wook Park ,  Yong Joon Jeon ,  Chul Keun Kim ,  Young Hee Choi ,  Jung Sun Kim ,  Nae Ri Park ,  Hendry Hendry ,  Byeong Moon Jeon ,  Joon Young Park

IPC分类号： H04N19/13 ,  H04N19/91 ,  H04N19/146 ,  H04N19/154 ,  H04N19/159 ,  H04N19/593 ,  H04N19/463 ,  H04N19/184 ,  H04N19/52 ,  H04N19/70 ,  H04N19/174

摘要： The present invention relates to an entropy encoding method, an entropy decoding method and to an apparatus using same. The entropy decoding method includes: a step of decoding a bin of a syntax element; and a step of acquiring information on the syntax element based on the decoded bin. In the step of decoding the bin, context-based decoding or bypass decoding is performed for each bin of the syntax element.

公开(公告)号：US20230083773A1

公开(公告)日：2023-03-16

申请号：US17897815

申请日：2022-08-29

申请人： TENCENT AMERICA LLC

发明人： Madhu PERINGASSERY KRISHNAN ,  Xin ZHAO ,  Shan LIU

IPC分类号： H04N19/13 ,  H04N19/91 ,  H04N19/159 ,  H04N19/18 ,  H04N19/176

摘要： This disclosure relates to secondary transform of video blocks with adaptive kernel options. For example, a method for decoding a video block in an video stream is disclosed. The method may include comprising parsing and processing the video stream to generate: a set of secondary transform coefficients associated with the video block; an intra-prediction mode associated with the video block; and a kernel index indicating a secondary transform kernel among a group of secondary transform kernels. The method may further include identifying the group of secondary transform kernels based on the intra-prediction mode; and performing an inverse secondary transform of the set of secondary transform coefficients to generate primary transform coefficients of the video block based on the secondary transform kernel among the group of secondary transform kernels identified by the kernel index. The quantity of kernels in the group of secondary transform kernels depends on at least one of: the intra-prediction mode associated with the video block; a size of the video block; or a primary transform type associated with the video block.

公开(公告)号：US20230077992A1

公开(公告)日：2023-03-16

申请号：US18056193

申请日：2022-11-16

申请人： CANON KABUSHIKI KAISHA

发明人： Guillaume LAROCHE ,  Christophe GISQUET ,  Patrice ONNO ,  Jonathan TAQUET

IPC分类号： H04N19/513 ,  H04N19/13 ,  H04N19/70 ,  H04N19/44

摘要： A method of encoding a motion information predictor index for an Affine Merge mode, comprising: generating a list of motion information predictor candidates; selecting one of the motion information predictor candidates in the list as an Affine Merge mode predictor; and generating a motion information predictor index for the selected motion information predictor candidate using CABAC coding, one or more bits of the motion information predictor index being bypass CABAC coded.

公开(公告)号：US20230061939A1

公开(公告)日：2023-03-02

申请号：US17978092

申请日：2022-10-31

申请人： Tencent Technology (Shenzhen) Company Limited

发明人： Ye HU ,  Liqiang WANG

IPC分类号： H04N19/129 ,  H04N19/176 ,  H04N19/167 ,  H04N19/13 ,  H04N19/184 ,  H04N19/186 ,  H04N19/172

摘要： A video decoding method includes obtaining a size of a coding block of a video image frame, and decoding a bitstream of the coding block to obtain a value of a range variable associated with a SRCC scan region of the coding block. The range variable includes a width range variable and a height range variable. Each of the width range variable and the height range variable are obtained by comparing a prefix value to one or more predefined value intervals. The method further includes determining a horizontal coordinate of boundary coordinates of the SRCC scan region according to a difference between the width of the coding block and the width range variable and determining a vertical coordinate of the boundary coordinates of the SRCC scan region according to a difference between the height of the coding block and the height range variable.

公开(公告)号：US11593632B2

公开(公告)日：2023-02-28

申请号：US15439893

申请日：2017-02-22

申请人： WaveOne Inc.

发明人： Oren Rippel ,  Lubomir Bourdev

IPC分类号： G06N3/08 ,  G06N3/04 ,  G06N20/00 ,  G06K9/62 ,  G06V10/44 ,  G06V10/75 ,  G06V20/40 ,  G06V20/52 ,  G06V30/10 ,  G06V30/194 ,  G06V40/16 ,  H04N19/126 ,  H04N19/167 ,  H04N19/172 ,  H04N19/196 ,  H04N19/91 ,  H04N19/44 ,  G06T5/00 ,  H04N19/13 ,  H04N19/149 ,  G06N3/084 ,  H04N19/18 ,  H04N19/48 ,  H04N19/154 ,  H04N19/33

摘要： A deep learning based compression (DLBC) system trains multiple models that, when deployed, generates a compressed binary encoding of an input image that achieves a reconstruction quality and a target compression ratio. The applied models effectively identifies structures of an input image, quantizes the input image to a target bit precision, and compresses the binary code of the input image via adaptive arithmetic coding to a target codelength. During training, the DLBC system reconstructs the input image from the compressed binary encoding and determines the loss in quality from the encoding process. Thus, the models can be continually trained to, when applied to an input image, minimize the loss in reconstruction quality that arises due to the encoding process while also achieving the target compression ratio.