-
公开(公告)号:US20240007663A1
公开(公告)日:2024-01-04
申请号:US18345223
申请日:2023-06-30
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor: Huanbang CHEN , Xiang MA , Haitao YANG , Jianle CHEN
IPC: H04N19/513 , H04N19/105 , H04N19/159 , H04N19/176 , H04N19/46
CPC classification number: H04N19/513 , H04N19/105 , H04N19/159 , H04N19/176 , H04N19/46
Abstract: This application provides a video picture prediction method and apparatus, to resolve a problem in a conventional technology that a length of a coded video sequence is increased. The first type of identifier may be added to a bitstream. The first type of identifier is used to indicate whether an affine motion model-based inter prediction mode is enabled for a video picture. For a video picture or a picture block included in the slice for which the affine motion model does not need to be used, a parameter, related to the affine motion model, of the picture block may not need to be transmitted. On a decoder side, during decoding of the picture block, the parameter related to the affine motion model does not need to be parsed. This can reduce load of a decoder, increase a processing speed, and decrease a processing time.
-
公开(公告)号:US20240007637A1
公开(公告)日:2024-01-04
申请号:US18368683
申请日:2023-09-15
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor: Xiang MA , Jue MAO , Haitao YANG
IPC: H04N19/13 , H04N19/91 , H04N19/132 , H04N19/172
CPC classification number: H04N19/13 , H04N19/91 , H04N19/132 , H04N19/172
Abstract: This application relates to the field of artificial intelligence (AI)-based video or picture compression technologies. The decoding method includes: performing probability estimation on input data by using a neural network, to obtain probability distribution of residual values of a plurality of samples and included in a residual of a current picture, where the input data includes at least a residual of a reference picture, and the reference picture is a decoded picture obtained before the current picture is decoded; performing arithmetic entropy decoding on a bitstream based on the probability distribution of the residual values of the plurality of samples and included in the residual of the current picture, to obtain first entropy decoding data, where the first entropy decoding data represents the residual of the current picture; and obtaining a reconstructed sample value of the current picture based on the residual of the current picture.
-
公开(公告)号:US20190297342A1
公开(公告)日:2019-09-26
申请号:US16440941
申请日:2019-06-13
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor: Xiang MA , Haitao YANG
IPC: H04N19/513 , H04N19/61 , H04N19/137 , H04N19/176
Abstract: A motion vector decoding method includes: determining a prediction motion vector of a to-be-decoded unit based on a motion vector of a prediction unit of the to-be-decoded unit; when a face image in which the to-be-decoded unit is located and at least one of a face image in which a first reference unit is located and a face image in which the prediction unit is located are not face images in a same orientation, performing a first update on the prediction motion vector, where the first update is used to determine a mapping vector that is of the prediction motion vector and that is in a plane of the face image in which the to-be-decoded unit is located; and obtaining a motion vector of the to-be-decoded unit based on the prediction motion vector obtained after the first update.
-
公开(公告)号:US20220094947A1
公开(公告)日:2022-03-24
申请号:US17541467
申请日:2021-12-03
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor: Xiang MA , Haitao YANG , Yin ZHAO , Lian ZHANG
IPC: H04N19/159 , H04N19/176 , H04N19/103 , H04N19/186 , H04N19/70
Abstract: This application discloses a method for constructing an MPM list, a method for obtaining an intra prediction mode of a chroma block, and an apparatus. In a specific implementation, a MIP mode is used for a current block, and the method for constructing an MPM list includes: obtaining intra prediction mode information of a neighboring block; determining, based on the intra prediction mode information of the neighboring block, whether an intra prediction mode of the neighboring block is the MIP mode; and skipping using the intra prediction mode of the neighboring block for MPM list construction of the current block if the intra prediction mode of the neighboring block is not the MIP mode; or using the intra prediction mode of the neighboring block for MPM list construction of the current block if the intra prediction mode of the neighboring block is the MIP mode.
-
公开(公告)号:US20210360235A1
公开(公告)日:2021-11-18
申请号:US17382421
申请日:2021-07-22
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor: Haitao YANG , Yuqun FAN , Xiang MA , Huanbang CHEN , Lian ZHANG
IPC: H04N19/112 , H04N19/105 , H04N19/513 , H04N19/70 , H04N19/82 , H04N19/172 , H04N19/137
Abstract: This application discloses a picture display order determining method which includes: obtaining a decoding order index value of a current picture and a decoding order index value of a previous picture that is adjacent to the current picture according to a decoding order; adding 1 to a cycle identifier value when the decoding order index value of the current picture is less than the decoding order index value of the previous picture; and determining a display order index value of the current picture based on a sum of the decoding order index value of the current picture and a preset positive integer multiple of the cycle identifier value. In this application, the display order index value of the current picture progressively increases based on a display order index value of a picture that is located before the current picture according to the decoding order.
-
公开(公告)号:US20210329296A1
公开(公告)日:2021-10-21
申请号:US17361692
申请日:2021-06-29
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
IPC: H04N19/593 , H04N19/186 , H04N19/176 , H04N19/167 , H04N19/105
Abstract: Apparatuses and methods for encoding and decoding are provided. The method for intra predicting a chroma sample of a block by applying cross-component linear model includes: obtaining reconstructed luma samples; determining maximum and minimum luma sample values based on the reconstructed luma samples; obtaining a difference of the maximum and minimum luma sample values. The method also includes: fetching a value out of a lookup table (LUT) by using a set of bits as an index, the set of bits following a position of the most-significant bit; obtaining linear model parameters based on the fetched value; and calculating a predicted chroma sample value by using the obtained linear model parameters. The efficiency to fetch the value out of the LUT is increased.
-
公开(公告)号:US20210274198A1
公开(公告)日:2021-09-02
申请号:US17325472
申请日:2021-05-20
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor: Xiang MA , Haitao YANG , Jianle CHEN
IPC: H04N19/186 , H04N19/159 , H04N19/176 , H04N19/105
Abstract: An intra prediction method and apparatus for reconstruction of unavailable reference samples are provided. The method includes obtaining an intra prediction mode of a current block, deriving availability of a reference sample of a component of the current block, substituting unavailable reference samples by using available reference samples, deriving a prediction of the current block based on the intra prediction mode and the substituted reference samples, and reconstructing the current block based on the prediction. The component includes a Cb component or a Cr component. Alternatively, the component includes a Chroma component. Since the method derives availability of the reference sample in each component, it can provide the available information more accurately.
-
公开(公告)号:US20190268608A1
公开(公告)日:2019-08-29
申请号:US16289250
申请日:2019-02-28
Inventor: Xiang MA , Haitao YANG , Li LI , Houqiang LI
IPC: H04N19/167 , H04N19/513 , H04N19/59 , H04N19/105 , H04N19/176
Abstract: Embodiments of the present invention provide a motion compensating prediction method and a motion compensating prediction apparatus. The motion compensating prediction method includes: determining a location of an initial reference pixel of a current pixel in a reference image, where the current pixel is located in a first sub-image of a current image; when the initial reference pixel is located outside a second sub-image that is in the reference image and that is at a location corresponding to the first sub-image, determining a location of a target reference pixel of the current pixel in the reference image based on the location of the initial reference pixel; and determining a predicted value of a pixel value of the current pixel based on a pixel value of the target reference pixel and/or a pixel value of a pixel near the target reference pixel.
-
公开(公告)号:US20240171773A1
公开(公告)日:2024-05-23
申请号:US18427084
申请日:2024-01-30
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
IPC: H04N19/593 , H04N19/105 , H04N19/167 , H04N19/176 , H04N19/186
CPC classification number: H04N19/593 , H04N19/105 , H04N19/167 , H04N19/176 , H04N19/186
Abstract: Apparatuses and methods for encoding and decoding are provided. The method for intra predicting a chroma sample of a block by applying cross-component linear model includes: obtaining reconstructed luma samples; determining maximum and minimum luma sample values based on the reconstructed luma samples; obtaining a difference of the maximum and minimum luma sample values. The method also includes: fetching a value out of a lookup table (LUT) by using a set of bits as an index, the set of bits following a position of the most-significant bit; obtaining linear model parameters based on the fetched value; and calculating a predicted chroma sample value by using the obtained linear model parameters. The efficiency to fetch the value out of the LUT is increased.
-
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.
-
-
-
-
-
-
-
-
-