公开(公告)号：US12271819B2

公开(公告)日：2025-04-08

申请号：US17371590

申请日：2021-07-09

Applicant: Huawei Technologies Co., Ltd.

Inventor： Jiafeng Zhu ,  Wei Wei ,  Jianle Chen ,  Wei Wang ,  Jie Shen

IPC: G06N3/082 ,  G06N3/04 ,  H03M7/30 ,  G06F11/34

Abstract: A first aspect relates to a computer-implemented method for performing model compression. The method includes compressing a machine learning (ML) network model comprising a multiple layer structure to produce a compressed ML network model. The compressed ML network model maintains the multiple layer structure of the ML network model. The method generates a model file for the compressed ML network model. The model file includes the compressed ML network model and decoding information for enabling the ML network model to be decompressed and executed layer-by-layer.

公开(公告)号：US12267532B2

公开(公告)日：2025-04-01

申请号：US18295986

申请日：2023-04-05

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Anand Meher Kotra ,  Semih Esenlik ,  Jianle Chen ,  Biao Wang ,  Han Gao ,  Zhijie Zhao

IPC: H04N19/96 ,  H04N19/172 ,  H04N19/52

Abstract: A video processing method, comprising: initializing a HMVP list for a current CTU row when the current CTU is the beginning CTU of a current CTU row; and processing the current CTU row based on the HMVP list. By performing the method, the encoding efficiency and decoding efficiency are improved.

公开(公告)号：US12212783B2

公开(公告)日：2025-01-28

申请号：US17702404

申请日：2022-03-23

Applicant: Huawei Technologies Co., Ltd.

Inventor： Fnu Hendry ,  Ye-Kui Wang ,  Jianle Chen

IPC: H04N19/70 ,  H04N19/169 ,  H04N19/172 ,  H04N19/174 ,  H04N19/44 ,  H04N19/46

Abstract: A method of decoding is provided. The method includes receiving a picture unit (PU) including zero or one picture header (PH) network abstraction layer (NAL) unit and only one coded picture; and decoding the only one coded picture from the PU to obtain a decoded picture. A corresponding method of encoding is also provided. The method includes generating a PU including zero or one PH NAL units and only one coded picture; encoding the PU into a video bitstream; and storing the video bitstream for communication toward a video decoder.

公开(公告)号：US20250030835A1

公开(公告)日：2025-01-23

申请号：US18770700

申请日：2024-07-12

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Alexey Konstantinovich FILIPPOV ,  Vasily Alexeevich RUFITSKIY ,  Jianle Chen

IPC: H04N19/105 ,  H04N19/117 ,  H04N19/136 ,  H04N19/186 ,  H04N19/196

Abstract: The present disclosure relates to the field of picture processing. In particular, the present disclosure relates to improving intra prediction (such as the chroma intra prediction) using a cross component linear model (CCLM) and, more particularly, relating to spatial filtering used in a cross-component linear model for intra prediction with different chroma formats. An apparatus, an encoder, a decoder and corresponding methods for cross-component prediction for a picture, in which the set of down-sampling filters applied during the prediction depends on a chroma format, that may be one of multiple supported chroma formats are provided, so as to improve coding efficiency.

公开(公告)号：US20250024018A1

公开(公告)日：2025-01-16

申请号：US18885854

申请日：2024-09-16

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Huanbang Chen ,  Haitao Yang ,  Jianle Chen ,  Weiwei Xu ,  Ting Fu ,  Jiali Fu

IPC: H04N19/105 ,  H04N19/119 ,  H04N19/132 ,  H04N19/159 ,  H04N19/176 ,  H04N19/70

Abstract: Technologies for inter prediction for a block in a video are provided. In one example, a method includes: when a size of a current block satisfies a preset condition, parsing a bitstream to obtain a syntax element, where the syntax element includes at least an index of optimal candidate motion information of the current block; determining, based on the syntax element, to construct a first list or a second list for the current block, where the first list is a block-based candidate motion information list, and the second list is a subblock-based candidate motion information list; determining optimal motion information from the first list or the second list based on the index; and predicting the current block based on the optimal motion information. In this method, the block-based candidate motion information list and the subblock-based candidate motion information list are distinguished from each other. This effectively reduces transmission costs of the optimal candidate motion information.

公开(公告)号：US12192513B2

公开(公告)日：2025-01-07

申请号：US18460607

申请日：2023-09-04

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Alexey Konstantinovich Filippov ,  Vasily Alexeevich Rufitskiy ,  Jianle Chen

IPC: H04N19/59 ,  H04N19/105 ,  H04N19/117 ,  H04N19/159 ,  H04N19/176 ,  H04N19/593

Abstract: Provided are a method, an apparatus, a computer program product and a non-transitory computer-readable medium for video coding. The method comprises performing an intra-prediction process of a block comprising samples to be predicted, wherein an interpolation filter is applied to reference samples of the block during the intra-prediction process of the block. The interpolation filter is selected on the basis of a subpixel offset between the reference samples and the samples to be predicted, and a size of a main reference side used in the intra-prediction process is determined according to a length of the interpolation filter and an intra-prediction mode that provides, out of a set of available intra-prediction modes, the greatest non-integer value of said subpixel offset, wherein the main reference side comprises the reference samples.

公开(公告)号：US12184839B2

公开(公告)日：2024-12-31

申请号：US18456528

申请日：2023-08-28

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Xiang Ma ,  Jianle Chen ,  Yin Zhao ,  Haitao Yang

IPC: H04N19/105 ,  H04N19/132 ,  H04N19/159 ,  H04N19/176 ,  H04N19/186

Abstract: An intra prediction method by using cross component liner prediction mode (CCLM), includes: determining a luma block corresponding to a current chroma block; obtaining luma reference samples of the luma block based on determining L available chroma reference samples of the current chroma block, wherein the obtained luma reference samples of the luma block are down-sampled luma reference samples; calculating linear model coefficients based on the luma reference samples and chroma reference samples that correspond to the luma reference samples; and obtaining a prediction for the current chroma block based on the linear model coefficients and values of a down-sampled luma block of the luma block.

公开(公告)号：US12177434B2

公开(公告)日：2024-12-24

申请号：US17486082

申请日：2021-09-27

Applicant: Huawei Technologies Co., Ltd.

Inventor： Han Gao ,  Semih Esenlik ,  Biao Wang ,  Anand Meher Kotra ,  Jianle Chen

IPC: H04N19/12 ,  H04N19/176 ,  H04N19/593 ,  H04N19/61

Abstract: A method of coding implemented by a decoding device or an encoding device comprises determining an intra prediction mode of a current block; and determining selecting of a secondary transform of the current block based on the intra prediction mode determined for the current block.

公开(公告)号：US12177427B2

公开(公告)日：2024-12-24

申请号：US18191267

申请日：2023-03-28

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Alexey Konstantinovich Filippov ,  Vasily Alexeevich Rufitskiy ,  Jianle Chen

IPC: H04N19/17 ,  H04N19/117 ,  H04N19/132 ,  H04N19/159 ,  H04N19/176 ,  H04N19/182 ,  H04N19/184 ,  H04N19/503 ,  H04N19/593

Abstract: Methods and devices for intra-prediction of a current block in video encoding or decoding are provided. A method includes: performing intra-prediction processing of the current block according to a directional intra-prediction mode, including applying reference sample filtering or subpixel interpolation filtering to reference samples in one or more reference blocks, wherein the directional intra-prediction mode is classified into one of the following groups: (A) vertical or horizontal modes, (B) directional modes including diagonal modes that represent angles which are multiples of 45 degrees, (C) remaining directional modes; if the directional intra-prediction mode is classified as belonging to group B, a reference sample filter is applied to the reference samples; if the directional intra-prediction mode is classified as belonging to group C, an intra reference sample interpolation filter is applied to the reference samples.

公开(公告)号：US12167009B2

公开(公告)日：2024-12-10

申请号：US17973151

申请日：2022-10-25

Applicant: Huawei Technologies Co., Ltd.

Inventor： Yin Zhao ,  Haitao Yang ,  Jianle Chen

IPC: H04N19/12 ,  H04N19/124 ,  H04N19/176 ,  H04N19/184 ,  H04N19/44 ,  H04N19/51 ,  H04N19/61 ,  H04N19/625

Abstract: A video processing method includes: obtaining prediction information of a CU; obtaining, when the CU comprises only one residual TU and a size of the residual TU is less than a size of the CU, a TU partitioning mode of the CU and a residual position of the residual TU, wherein the TU partitioning mode and the residual position are used to determine a horizontal transform type and a vertical transform type; obtaining transform coefficients of the residual TU based on the horizontal transform type and the vertical transform type; and generating a bitstream that is for storing or transmitting and that includes the prediction information, a first flag that indicates the TU partitioning mode, a second flag that indicates the residual position, and the transform coefficients.