公开(公告)号：US20220345751A1

公开(公告)日：2022-10-27

申请号：US17857941

申请日：2022-07-05

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Roman Igorevich Chernyak ,  Timofey Mikhailovich Solovyev ,  Alexander Alexandrovich Karabutov ,  Sergey Yurievich Ikonin ,  Elena Alexandrovna Alshina

IPC: H04N19/70

Abstract: A method for decoding of a video bitstream implemented by a decoding device, wherein the video bitstream includes data representing one or more sequence parameter set, SPS, flags, the method comprising: for an SPS flag of the one or more SPS flags, obtaining two variables of the SPS flag, respectively, by parsing the video bitstream, wherein the value of one variable of the two variables is the minimum allowed value of the SPS flag, and wherein the value of the other variable of the two variables is the maximum allowed value of the SPS flag; obtaining the SPS flag, by parsing the video bitstream; evaluating whether the value of the SPS flag is valid based on the values of the two variables; and in case that the value of the SPS flag is valid, decoding the video bitstream according to the value of the SPS flag.

公开(公告)号：US20220345729A1

公开(公告)日：2022-10-27

申请号：US17847127

申请日：2022-06-22

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Timofey Mikhailovich Solovyev ,  Roman Igorevich Chernyak ,  Alexander Alexandrovich Karabutov ,  Sergey Yurievich Ikonin ,  Elena Alexandrovna Alshina

IPC: H04N19/196 ,  H04N19/13 ,  H04N19/70 ,  H04N19/176 ,  H04N19/167 ,  H04N19/96

Abstract: Improved deriving and signaling of minimum and maximum block sizes in the context of partitioning processes is provided herein. In particular, it is provided a method of deriving a minimum coding block size implemented by a decoding device, comprising: parsing a value of a syntax element from a bitstream, deriving the binary logarithm of the minimum coding block size by adding 2 to the parsed value of the syntax element, and deriving the minimum block size from the derived binary logarithm of the minimum coding block size. Restrictions on the syntax element values related to the partitioning process are introduced to prevent undefined behavior and unpredictable code length in case of using variable length codes.

公开(公告)号：US20220264094A1

公开(公告)日：2022-08-18

申请号：US17708861

申请日：2022-03-30

Applicant: Huawei Technologies Co., Ltd.

Inventor： Timofey Mikhailovich Solovyev ,  Maxim Borisovitch Sychev ,  Huanbang Chen ,  Alexander Alexandrovich Karabutov ,  Roman Igorevich Chernyak ,  Sergey Yurievich Ikonin ,  Haitao Yang ,  Elena Alexandrovna Alshina

IPC: H04N19/122 ,  H04N19/176 ,  H04N19/547 ,  H04N19/523

Abstract: A method related to adaptive usage of pixel-based and block-based affine motion compensation and includes performing sub-block-based affine transform prediction on an affine block with a first sub-block size if the first sub-block size is greater than or equal to a first sub-block size threshold. If the first sub-block size is less than the first sub-block size threshold, it is determined whether a pixel-based motion vector field is not applied for performing motion compensation for the affine block. If the motion vector field is not applied, a sub-block-based affine motion prediction is performed with a second sub-block size that is based on the first sub-block size. If the pixel-based motion vector field is applied, motion compensation is performed for a sub-block of the affine block using the pixel-based motion vector field.

公开(公告)号：US11375199B2

公开(公告)日：2022-06-28

申请号：US16850854

申请日：2020-04-16

Applicant: Huawei Technologies Co., Ltd.

Inventor： Maxim Borisovitch Sychev ,  Georgy Aleksandrovich Zhulikov ,  Timofey Mikhailovich Solovyev ,  Jianle Chen

IPC: H04N7/18 ,  H04N19/132 ,  H04N19/105 ,  H04N19/117 ,  H04N19/137 ,  H04N19/159 ,  H04N19/176 ,  H04N19/182 ,  H04N19/52 ,  H04N19/593

Abstract: The disclosure relates to an apparatus and method for inter prediction of a sample value of a current full-integer pixel of a plurality of pixels of a current block of a current frame of a video signal. The apparatus comprises a processing unit configured to: determine a motion vector of the current full-integer pixel on the basis of the current frame and a reference frame of the video signal and/or on the basis of a motion compensation model; determine for the current full-integer pixel a corresponding sub-integer pixel in the reference frame on the basis of the motion vector of the current full-integer pixel; generate on the basis of a predefined set of filter support pixels in the current frame a set of corresponding filter support pixels in the reference frame, wherein the predefined set of filter support pixels in the current frame comprises one or more neighboring full-integer and/or sub-integer pixels of the current full-integer pixel; determine a respective sample value of the corresponding sub-integer pixel of the current full-integer pixel and the corresponding filter support pixels in the reference frame; and determine the inter predicted sample value of the current pixel in the current frame by applying a spatial high-pass filter to the sample value of the corresponding sub-integer pixel of the current full-integer pixel in the reference frame and to the sample values of the corresponding filter support pixels in the reference frame.

公开(公告)号：US20250008128A1

公开(公告)日：2025-01-02

申请号：US18884321

申请日：2024-09-13

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Timofey Mikhailovich Solovyev ,  Esin Koyuncu ,  Alexander Alexandrovich Karabutov ,  Maxim Borisovitch Sychev ,  Mikhail Vyacheslavovich Sosulnikov ,  Sergey Yurievich Ikonin ,  Elena Alexandrovna Alshina

IPC: H04N19/189 ,  H04N19/13 ,  H04N19/42

Abstract: A neural network including at least one neural network layer and an activation function connected to an output of the at least one neural network layer. The activation function is implemented as an approximation function of a mathematically defined real valued non-linear activation function, wherein the approximation function allows for integer-only processing of fixed-point representations of input values of the approximation function.

公开(公告)号：US20250005331A1

公开(公告)日：2025-01-02

申请号：US18885411

申请日：2024-09-13

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Timofey Mikhailovich Solovyev ,  Sergey Yurievich Ikonin ,  Elena Alexandrovna Alshina ,  Johannes Sauer ,  Esin Koyuncu ,  Maxim Borisovitch Sychev ,  Alexander Alexandrovich Karabutov ,  Mikhail Vyacheslavovich Sosulnikov ,  Kirill Igorevich SOLODSKIKH ,  Vladimir Mikhailovich Kryzhanovskiy ,  Alexander Nikolaevich Filippov

IPC: G06N3/0455 ,  G06T9/00

Abstract: The present disclosure relates to a method of operating a neural network with clipped input data. The method includes defining lower and upper threshold values for integer numbers in data entities of input data for at least one neural network layer. If a value of an integer number in a data entity of the input data is smaller than the defined lower threshold value, the method includes clipping the value of the integer number comprised in the data entity of the input data to the defined lower threshold value. If a value of an integer number in a data entity of the input data is larger than the defined upper threshold value, the method includes clipping the value of the integer number comprised in the data entity of the input data to the defined upper threshold value. Integer overflow of an accumulator register is thereby avoided.

公开(公告)号：US20250005330A1

公开(公告)日：2025-01-02

申请号：US18883907

申请日：2024-09-12

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Timofey Mikhailovich Solovyev ,  Sergey Yurievich Ikonin ,  Elena Alexandrovna Alshina ,  Esin Koyuncu ,  Maxim Borisovitch Sychev ,  Alexander Alexandrovich Karabutov ,  Mikhail Vyacheslavovich Sosulnikov

IPC: G06N3/0455

Abstract: A method of operating a neural network based on conditioned weights includes defining integer lower and upper threshold values for values of integer numbers comprised in data entities of input data for the neural network layer. If a value of an integer numbers comprised in a data entity of the input data is smaller than the lower threshold value, the value of the integer number comprised in the data entity of the input data is clipped to the lower threshold value, or if a value of an integer number comprised in a data entity of the input data is larger than the upper threshold value, the value of the integer number comprised in the data entity of the input data is clipped to the upper threshold value. Integer valued weights are determined based on the lower threshold value, the upper threshold value, and a pre-defined accumulator register size, such that integer overflow of the accumulator register can be avoided.

公开(公告)号：US12160578B2

公开(公告)日：2024-12-03

申请号：US17509324

申请日：2021-10-25

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Sergey Yurievich Ikonin ,  Roman Igorevich Chernyak ,  Timofey Mikhailovich Solovyev ,  Alexander Alexandrovich Karabutov ,  Jianle Chen ,  Elena Alexandrovna Alshina

IPC: H04N19/17 ,  H04N19/124 ,  H04N19/126 ,  H04N19/132 ,  H04N19/172 ,  H04N19/174 ,  H04N19/184 ,  H04N19/186 ,  H04N19/44

Abstract: A method of obtaining a chrominance quantization parameter (QP) for chrominance components based on a luminance QP for luminance component, wherein the method is performed by a decoder, comprising parsing a received bitstream to obtain the luminance QP and information of a mapping function (ƒ) which associates a QP index (QPi) to the chrominance QP (QPc); obtaining the QPi based at least in a part on the luminance QP; obtaining the mapping function based on the obtained information; and obtaining a QPc based on the obtained mapping function and the obtained QPi.

公开(公告)号：US20240283966A1

公开(公告)日：2024-08-22

申请号：US18585826

申请日：2024-02-23

Applicant: Huawei Technologies Co., Ltd.

Inventor： Timofey Mikhailovich Solovyev ,  Jianle Cheng ,  Sergey Yurievich Ikonin

IPC: H04N19/52 ,  H04N19/169

CPC classification number: H04N19/52 ,  H04N19/169

Abstract: Motion vectors (MVs) are used as predictors for prediction of an image for a current coding unit (CU) within a current video frame. The MVs are from a list of motion vector candidates (MVCs), which is generated. The list includes MVs determined from a first or second pattern, each pattern specifying MVC positions. The first MV positions are within a current video frame, while the second MV positions are for a video frame different from the current frame. The MVC list is generated for a current CU with the MV positions being relative to a position of the current CU. In particular, the MVC list is generated in dependence on a size of the current CU and a size of a grid specifying a minimum distance between two MV positions. One or more MVs as specified by the MV positions of said pattern are included into the MVC list.

公开(公告)号：US12047609B2

公开(公告)日：2024-07-23

申请号：US17707202

申请日：2022-03-29

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Timofey Mikhailovich Solovyev ,  Maxim Borisovitch Sychev ,  Huanbang Chen ,  Alexander Alexandrovich Karabutov ,  Roman Igorevich Chernyak ,  Sergey Yurievich Ikonin ,  Haitao Yang ,  Elena Alexandrovna Alshina

IPC: H04N19/82 ,  H04N19/105 ,  H04N19/109 ,  H04N19/117 ,  H04N19/132 ,  H04N19/139 ,  H04N19/176 ,  H04N19/182 ,  H04N19/196 ,  H04N19/52 ,  H04N19/80

CPC classification number: H04N19/80 ,  H04N19/105 ,  H04N19/109 ,  H04N19/117 ,  H04N19/132 ,  H04N19/139 ,  H04N19/176 ,  H04N19/182 ,  H04N19/197 ,  H04N19/52

Abstract: An apparatus for inter prediction of a sample value of a current full-integer pixel of a plurality of pixels associated with a current block of a current frame of a video signal is disclosed. The apparatus is configured to: determine a motion vector of the current full-integer pixel based on a motion compensation model; determine for the current full-integer pixel a corresponding sub-integer pixel in a reference frame; determine positions of a set of corresponding filter support pixels in the reference frame; obtain a respective sample value of the corresponding sub-integer pixel of the current full-integer pixel and the corresponding filter support pixels in the reference frame by applying a bilinear interpolation; and determine the inter predicted sample value of the current full-integer pixel.