公开(公告)号：US20250056003A1

公开(公告)日：2025-02-13

申请号：US18807369

申请日：2024-08-16

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Huanbang CHEN ,  Haitao YANG ,  Jianle CHEN ,  Jiali FU

IPC: H04N19/139 ,  H04N19/119 ,  H04N19/176 ,  H04N19/61

Abstract: A motion vector prediction method includes parsing a bitstream to obtain an index value of a candidate motion vector list and constructing the candidate motion vector list that includes. candidate motion vectors of K control points of a current block. The candidate motion vectors of K control points are obtained based on a 2N-parameter affine transform model used for a neighboring block of the current block, where N and K are integers greater than or equal to 2 and less than or equal to 4 with N not being equal to K. The method further includes determining, in the candidate motion vector list, target candidate motion vectors of the K control points based on the index value and obtaining a predicted motion vector of each subblock of the current block based on the target candidate motion vectors of the K control points.

公开(公告)号：US20240331117A1

公开(公告)日：2024-10-03

申请号：US18743607

申请日：2024-06-14

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Weiwei XU ,  Haitao YANG ,  Quanhe YU ,  Hu CHEN ,  Yichuan WANG

IPC: G06T5/90 ,  G06T7/11 ,  G06T15/00

CPC classification number: G06T5/90 ,  G06T7/11 ,  G06T15/00

Abstract: A dynamic range mapping method and apparatus for a panoramic video that relate to the field of video image processing are provided. The method includes: splitting a two-dimensional panoramic projection image corresponding to any frame of three-dimensional panoramic image in a panoramic video, to obtain a plurality of regions of the two-dimensional panoramic projection image; obtaining metadata of the two-dimensional panoramic projection image, where the metadata includes metadata information elements separately corresponding to the plurality of regions, and a metadata information element corresponding to one region includes dynamic mapping information of the region; determining dynamic mapping information of each pixel in a current angle of view range based on respective dynamic mapping information of the plurality of regions; and performing dynamic range mapping on each pixel in the current angle of view range, to obtain a two-dimensional panoramic projection image that is used for display or subsequent processing.

公开(公告)号：US20240305784A1

公开(公告)日：2024-09-12

申请号：US18665853

申请日：2024-05-16

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Yin ZHAO ,  Haitao YANG ,  Jianle CHEN

IPC: H04N19/132 ,  H04N19/159 ,  H04N19/169 ,  H04N19/176 ,  H04N19/186 ,  H04N19/96

CPC classification number: H04N19/132 ,  H04N19/159 ,  H04N19/176 ,  H04N19/186 ,  H04N19/1883 ,  H04N19/96

Abstract: Embodiments of this application disclose an intra prediction method for a video sequence. The method includes: obtaining a size and a split mode of a chroma coding tree node; determining, based on the size and the split mode of the chroma coding tree node, whether to allow cross-component linear model (CCLM) intra prediction to be performed on a chroma coding unit included in the chroma coding tree node; determining a prediction mode of the chroma coding unit depending on whether to allow CCLM to be performed on the chroma coding unit; and processing the chroma coding unit based on the prediction mode of the chroma coding unit to obtain prediction samples of the chroma coding unit.

公开(公告)号：US20240233335A1

公开(公告)日：2024-07-11

申请号：US18616599

申请日：2024-03-26

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Dequan YU ,  Yin ZHAO ,  Haitao YANG

IPC: G06V10/77 ,  G06V10/774 ,  G06V10/82

CPC classification number: G06V10/7715 ,  G06V10/774 ,  G06V10/82

Abstract: A feature map processing method includes: determining P target strides based on a preset correspondence between a stride and a feature map size range and a size of a target feature map, where P is a positive integer; and invoking a neural network model to process the target feature map, to obtain a processing result of the target feature map, where the neural network model includes P dynamic stride modules, a stride of a dynamic stride module of the P dynamic stride modules is a target stride corresponding to a dynamic stride module in the P target strides.

公开(公告)号：US20240221230A1

公开(公告)日：2024-07-04

申请号：US18604842

申请日：2024-03-14

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Yibo SHI ,  Yunying GE ,  Jing WANG ,  Jue MAO ,  Yin ZHAO ,  Haitao YANG

IPC: G06T9/00

CPC classification number: G06T9/001 ,  G06T9/002

Abstract: This application provides a feature map encoding and decoding method and an apparatus, and relates to the field of artificial intelligence (AI)-based data encoding and decoding technologies. The feature map decoding method includes: obtaining a bitstream of a to-be-decoded feature map, where the to-be-decoded feature map includes a plurality of feature elements; obtaining a first probability estimation result corresponding to each feature element based on the bitstream, where the first probability estimation result includes a first peak probability; determining a set of first feature elements and a set of second feature elements from the plurality of feature elements based on a first threshold and the first peak probability corresponding to each feature element; and obtaining a decoded feature map based on the set of first feature elements and the set of second feature elements. This can improve encoding and decoding performance while reducing encoding and decoding complexity.

公开(公告)号：US20240135491A1

公开(公告)日：2024-04-25

申请号：US18400522

申请日：2023-12-29

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Yin ZHAO ,  Jue MAO ,  Haitao YANG

IPC: G06T3/4046 ,  G06T7/60

CPC classification number: G06T3/4046 ,  G06T7/60 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: This application relates to the field of artificial intelligence technologies, and provides a feature map processing method and a related device. The method is implemented by invoking a neural network model that includes a plurality of input adaptation branches and a post-processing part. An output of each of the plurality of input adaptation branches is an input of the post-processing part, and each of the plurality of input adaptation branches can downsample a feature map at a different ratio.

公开(公告)号：US20230239516A1

公开(公告)日：2023-07-27

申请号：US18191990

申请日：2023-03-29

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Jue MAO ,  Haitao YANG ,  Xiang MA

IPC: H04N19/91 ,  H04N19/132 ,  H04N19/172 ,  H04N19/176 ,  H04N19/50 ,  H04N19/42 ,  H04N19/70

CPC classification number: H04N19/91 ,  H04N19/132 ,  H04N19/172 ,  H04N19/176 ,  H04N19/50 ,  H04N19/42 ,  H04N19/70

Abstract: The technology of this application relates to an entropy encoding method that includes obtaining base layer information of a to-be-encoded picture block, where the base layer information corresponds to M samples in the picture block, and M is a positive integer, obtaining K elements corresponding to enhancement layer information of the picture block, where the enhancement layer information corresponds to N samples in the picture block, both K and N are positive integers, and N≥M, inputting the base layer information into a neural network to obtain K groups of probability values, where the K groups of probability values correspond to the K elements, and any group of probability values is for representing probabilities of a plurality of candidate values of a corresponding element, and performing entropy encoding on the K elements based on the K groups of probability values.

公开(公告)号：US20230232036A1

公开(公告)日：2023-07-20

申请号：US17994556

申请日：2022-11-28

Applicant: HUAWEI TECHNOLOGIES CO.,LTD.

Inventor： Xiang MA ,  Haitao YANG ,  Huanbang CHEN ,  Shan GAO

IPC: H04N19/52 ,  H04N19/176 ,  H04N19/182

CPC classification number: H04N19/52 ,  H04N19/176 ,  H04N19/182

Abstract: A picture prediction method is provided, which includes: obtaining initial motion information of a current picture block; determining, based on a matching cost criterion, that positions of a pair of reference blocks are a position of a target forward reference block of the current picture block and a position of a target backward reference block of the current picture block, where positions of each pair of reference blocks include a position of a forward reference block and a position of a backward reference block; and for the positions of each pair of reference blocks, a first position offset and a second position offset are in a mirror relationship; and obtaining a predicted value of a pixel value of the current picture block based on a pixel value of the target forward reference block and a pixel value of the target backward reference block.

公开(公告)号：US20230156202A1

公开(公告)日：2023-05-18

申请号：US18098997

申请日：2023-01-19

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Xiang MA ,  Jianle CHEN ,  Haitao YANG

IPC: H04N19/196 ,  H04N19/132 ,  H04N19/159 ,  H04N19/176 ,  H04N19/186 ,  H04N19/593

CPC classification number: H04N19/196 ,  H04N19/132 ,  H04N19/159 ,  H04N19/176 ,  H04N19/186 ,  H04N19/593

Abstract: This application provides a chroma block prediction method and apparatus. The method includes: obtaining a maximum luma value and a minimum luma value based on luma samples corresponding to neighboring samples of a target chroma block, and calculating a first difference between the maximum luma value and the minimum luma value; if the first difference is not equal to 0, processing the first difference based on a quantity of significant bits of the first difference and a first preset bit depth to obtain a second difference; and determining, based on a first chroma value, a second chroma value, and the second difference, an intra prediction model parameter corresponding to the target chroma block, and determining prediction information of the target chroma block based on the intra prediction model parameter and luma reconstruction information corresponding to the target chroma block.

公开(公告)号：US20230070282A1

公开(公告)日：2023-03-09

申请号：US17898044

申请日：2022-08-29

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Huanbang Chen ,  Yin ZHAO ,  Haitao YANG ,  Jianle CHEN

IPC: H04N19/513 ,  H04N19/176 ,  H04N19/189

Abstract: This application provides a motion vector obtaining method and apparatus. The method includes: determining a target offset vector of a block and identifier information of a target picture, wherein the block comprises at least one sub-block; determining a location of the sub-block; determining, as a target location coordinate value of a collocated sub-block, a location coordinate value obtained by performing a clipping operation on an initial location coordinate value in a range, wherein the initial location coordinate value is based on the location of the sub-block and the target offset vector; and obtaining a motion vector of the sub-block based on a motion vector corresponding to the target location coordinate value. Thus, a range of the target offset vector is limited, so that a quantity of memory read times can be reduced in a process of obtaining the motion vector of the collocated sub-block.