公开(公告)号：US20210266552A1

公开(公告)日：2021-08-26

申请号：US17319098

申请日：2021-05-13

Applicant: HUAWEI TECHNOLOGIES CO.,LTD.

Inventor： Anand Meher Kotra ,  Elena Alexandrovna Alshina ,  Semih Esenlik ,  Biao Wang ,  Han Gao ,  Roman Igorevich Chernyak

IPC: H04N19/124 ,  H04N19/176 ,  H04N19/186 ,  H04N19/117

Abstract: A method for deblocking a chroma block edge between a first chroma block of a first image block and a second chroma block of a second image block. The method includes a decision process which includes: determining a first chroma quantization parameter for the first chroma block based on a first luma quantization parameter of a first luma block of the first image block and a chroma QP mapping table for the first chroma block; determining a second chroma quantization parameter for the second chroma block based on a second luma quantization parameter of a second luma block of the second image block and a chroma QP mapping table for the second chroma block; determining an averaged and rounded chroma quantization parameter based on the first chroma quantization parameter and the second chroma quantization parameter; and determining a threshold parameter based on the averaged and rounded chroma quantization parameter.

公开(公告)号：US20210211657A1

公开(公告)日：2021-07-08

申请号：US17203261

申请日：2021-03-16

Applicant: Huawei Technologies Co., Ltd.

Inventor： Sergey Yurievich Ikonin ,  Victor Alexeevich Stepin ,  Alexander Alexandrovich Karabutov ,  Elena Alexandrovna Alshina ,  Roman Igorevich Chernyak ,  Jianle Chen ,  Dmitry Yurievich Kuryshev

IPC: H04N19/117 ,  H04N19/176 ,  H04N19/82 ,  H04N19/70 ,  H04N19/184

Abstract: A filter is configured for processing a reconstructed frame for generation of a filtered reconstructed frame, and wherein the reconstructed frame comprises a plurality of pixels. The filter includes one or more processor configured to scan a current pixel of the reconstructed block and its neighboring pixels of the current pixel according to a predefined scan template, obtain spectrum components by performing transform for the current pixel and its neighboring pixels, obtain filtered spectrum components based on a filtering parameter and the spectrum components, obtain filtered pixels by performing inverse transform for the filtered spectrum components, and generate a filtered reconstructed block based on the filtered pixels.

公开(公告)号：US20250142066A1

公开(公告)日：2025-05-01

申请号：US19007327

申请日：2024-12-31

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Johannes Sauer ,  Panqi Jia ,  Elena Alexandrovna Alshina ,  Atanas Boev

IPC: H04N19/119 ,  H04N19/176 ,  H04N19/186

Abstract: The present disclosure relates to picture encoding and decoding of image regions on tile-basis. In particular, multiple components of an input tensor including a first and second component in spatial dimensions is processed within multiple pipelines. The processing of the first component includes dividing the first component in the spatial dimensions into a first plurality of tiles. Likewise, the processing of the second component includes dividing the second component in the spatial dimensions into a second plurality of tiles. The respective first and second plurality of tiles are then processed each separately. Among the first and second plurality of tiles there are at least two respective collocated tiles differing in size. In case of compression, the processing of the first and/or second component includes picture encoding, rate distortion optimization quantization, and picture filtering. In case of decompression, the processing includes picture decoding and picture filtering.

公开(公告)号：US12284390B2

公开(公告)日：2025-04-22

申请号：US18336735

申请日：2023-06-16

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Semih Esenlik ,  Panqi Jia ,  Elena Alexandrovna Alshina

IPC: H04N19/70 ,  H04N19/119 ,  H04N19/132 ,  H04N19/167 ,  H04N19/172 ,  H04N19/42

Abstract: For picture decoding and encoding of neural-network-based bitstreams, a picture is represented by an input set of samples which is obtained from the bitstream. The picture is reconstructed from output subsets, which are generated as a result of processing the input set L. The input set is divided into multiple input subsets Li. The input subsets are each subject to processing with a neural network having one or more layers. The neural network uses as input multiple samples of an input subset and generates one sample of an output subset. By combining the output subsets, the picture is reconstructed. In particular, the size of at least one input subset is smaller than a size that is required to obtain the size of the respective output subset, after processing by the one or more layers of the neural network.

公开(公告)号：US12250410B2

公开(公告)日：2025-03-11

申请号：US17951499

申请日：2022-09-23

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Biao Wang ,  Semih Esenlik ,  Elena Alexandrovna Alshina ,  Anand Meher Kotra ,  Han Gao

IPC: H04N19/70 ,  H04N19/172 ,  H04N19/187

Abstract: A method of decoding of a video or picture bitstream implemented by a decoding device, the bitstream including a current sequence parameter set (SPS) comprising syntax elements that apply to a video sequence, the method comprising: obtaining a first syntax element used to determine a maximum number of temporal sublayers that is allowed to be present in each coded layer video sequence) referring to the current SPS, wherein a value of the first syntax element is in a range of 0 to a first value, wherein the first value is a value of a second syntax element used to determine the maximum number of temporal sublayers that is allowed to present in a layer in each coded video sequence referring to a video parameter set, when the second syntax element is referred to by the SPS; decoding the bitstream based on the value of the first syntax element.

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：US12088820B2

公开(公告)日：2024-09-10

申请号：US17896012

申请日：2022-08-25

Applicant: Huawei Technologies Co., Ltd.

Inventor： Semih Esenlik ,  Biao Wang ,  Anand Meher Kotra ,  Elena Alexandrovna Alshina

IPC: H04N19/593 ,  H04N19/14 ,  H04N19/174 ,  H04N19/423

CPC classification number: H04N19/14 ,  H04N19/174 ,  H04N19/423

Abstract: A method of coding performed by a decoding device and a decoder are disclosed. The method comprises: obtaining a bitstream for a current picture; obtaining a quantity of tiles in a tile row of the current picture; obtaining a value of an address of a current slice, the current slice is comprised in the current picture; obtaining a value of a horizontal coordinate according to the value of the address of the current slice; parsing an indication value for a slice width from the bitsteam for the current picture, when a difference value between the quantity of tiles in the tile row of the current picture and the value of the horizontal coordinate is not equal to a first threshold.