公开(公告)号：US20240161488A1

公开(公告)日：2024-05-16

申请号：US18479611

申请日：2023-10-02

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Timofey Mikhailovich Solovyev ,  Elena Alexandrovna Alshina ,  Biao Wang ,  Alexander Alexandrovich Karabutov ,  Mikhail Vyacheslavovich Sosulnikov ,  Georgy Petrovich Gaikov ,  Han Gao ,  Panqi Jia ,  Esin Koyuncu ,  Sergey Yurievich Ikonin ,  Semih Esenlik

IPC: G06V10/82 ,  G06V10/77 ,  G06V20/40 ,  H04N19/513 ,  H04N19/91

CPC classification number: G06V10/82 ,  G06V10/7715 ,  G06V20/46 ,  H04N19/521 ,  H04N19/91

Abstract: This application provides methods and apparatuses for processing of picture data or picture feature data using a neural network with two or more layers. The present disclosure may be applied in the field of artificial intelligence (AI)-based video or picture compression technologies, and in particular, to the field of neural network-based video compression technologies. According to some embodiments, two kinds of data are combined during the processing including processing by the neural network. The two kinds of data are obtained from different stages of processing by the network. Some of the advantages may include greater scalability and a more flexible design of the neural network architecture which may further lead to better encoding/decoding performance.

公开(公告)号：US20240037802A1

公开(公告)日：2024-02-01

申请号：US18479507

申请日：2023-10-02

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Timofey Mikhailovich Solovyev ,  Biao Wang ,  Elena Alexandrovna Alshina ,  Han Gao ,  Panqi Jia ,  Esin Koyuncu ,  Alexander Alexandrovich Karabutov ,  Mikhail Vyacheslavovich Sosulnikov ,  Semih Esenlik ,  Sergey Yurievich Ikonin

IPC: G06T9/00 ,  G06T3/40

CPC classification number: G06T9/002 ,  G06T3/4046

Abstract: This application provides methods and apparatuses for processing of picture data or picture feature data using a neural network with two or more layers. The present disclosure may be applied in the field of artificial intelligence (AI)-based video or picture compression technologies, and in particular, to the field of neural network-based video compression technologies. According to some embodiments, position within the neural network, at which auxiliary information may be entered for processing is selectable based on a gathering condition. The gathering condition may assess whether some prerequisite is fulfilled. Some of the advantages may include better performance in terms of rate and/or disclosure due to the effect of increased flexibility in neural network configurability.

公开(公告)号：US20230128496A1

公开(公告)日：2023-04-27

申请号：US18145569

申请日：2022-12-22

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Maxim Borisovitch Sychev ,  Elena Alexandrovna Alshina ,  Mikhail Vyacheslavovich Sosulnikov ,  Alexander Alexandrovich Karabutov

IPC: H04N19/137 ,  H04N19/132 ,  H04N19/105 ,  H04N19/172

Abstract: Methods and apparatuses are provided for estimating motion vectors of a dense motion field based on subsampled sparse motion field. The sparse motion field includes two or more motion vectors with their respective start positions. For each of the motion vectors, a transformation is derived which transforms the motion vector from its start point into a target point. The transformed motion vectors then contribute to the estimated motion vector on the target position. The contribution of each motion vector is weighted. Such motion estimation may be readily used for video encoding and decoding.

公开(公告)号：US12184863B2

公开(公告)日：2024-12-31

申请号：US18145569

申请日：2022-12-22

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Maxim Borisovitch Sychev ,  Elena Alexandrovna Alshina ,  Mikhail Vyacheslavovich Sosulnikov ,  Alexander Alexandrovich Karabutov

IPC: H04N19/137 ,  H04N19/105 ,  H04N19/132 ,  H04N19/172

Abstract: Methods and apparatuses are provided for estimating motion vectors of a dense motion field based on subsampled sparse motion field. The sparse motion field includes two or more motion vectors with their respective start positions. For each of the motion vectors, a transformation is derived which transforms the motion vector from its start point into a target point. The transformed motion vectors then contribute to the estimated motion vector on the target position. The contribution of each motion vector is weighted. Such motion estimation may be readily used for video encoding and decoding.

公开(公告)号：US20240340425A1

公开(公告)日：2024-10-10

申请号：US18749362

申请日：2024-06-20

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Mikhail Vyacheslavovich Sosulnikov ,  Sergey Yurievich Ikonin ,  Andrey Soroka ,  Elena Alexandrovna Alshina

IPC: H04N19/13 ,  H04N19/103 ,  H04N19/136 ,  H04N19/184

CPC classification number: H04N19/13 ,  H04N19/103 ,  H04N19/136 ,  H04N19/184

Abstract: The present disclosure provides a method of decoding an encoded signal. The method includes receiving at least one bitstream comprising an encoded signal, the signal being entropy encoded with one or more Gaussian mixture models (GMMs), and the at least one bitstream comprising information for obtaining parameters of the one or more GMMs. The method further includes obtaining the GMM parameters based on the information from the at least one bitstream; and entropy decoding the signal using the GMMs with the obtained GMM parameters. The present disclosure further refers to a corresponding encoding method, decoder and encoder.

公开(公告)号：US20230262243A1

公开(公告)日：2023-08-17

申请号：US18304214

申请日：2023-04-20

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Sergey Yurievich Ikonin ,  Alexander Alexandrovich Karabutov ,  Mikhail Vyacheslavovich Sosulnikov ,  Victor Alexeevich Stepin ,  Elena Alexandrovna Alshina

IPC: H04N19/42 ,  H04N19/167 ,  H04N19/70 ,  H04N19/136 ,  H04N19/154 ,  H04N19/60 ,  H04N19/13 ,  H04N19/17 ,  H04N19/184

CPC classification number: H04N19/42 ,  H04N19/167 ,  H04N19/70 ,  H04N19/136 ,  H04N19/154 ,  H04N19/60 ,  H04N19/13 ,  H04N19/17 ,  H04N19/184

Abstract: The present disclosure relates to efficient signaling of feature map information for a system employing a neural network. In particular, at the decoder side, a presence indicator is obtained based on information parsed from a bitstream. Based on the value of the obtained presence indicator, further data related to a feature map region are parsed or the parsing is bypassed. The presence indicator may be, for instance, a region presence indicator indicating whether feature map data is included in the bitstream or may be a side information presence indicator indicating whether a side information related to the feature map data is included in the bitstream. Similarly, an encoding method, as well as encoding and decoding devices, are provided. Accordingly, feature map data may be processed more efficiently, by reducing decoding complexity, and the amount of transmitted data can be reduced by applying the bypassing.

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：US20230353764A1

公开(公告)日：2023-11-02

申请号：US18340704

申请日：2023-06-23

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Sergey Yurievich Ikonin ,  Mikhail Vyacheslavovich Sosulnikov ,  Alexander Alexandrovich Karabutov ,  Timofey Mikhailovich Solovyev ,  Biao Wang ,  Elena Alexandrovna Alshina

IPC: H04N19/139 ,  H04N19/59 ,  H04N19/70 ,  H04N19/33

CPC classification number: H04N19/33 ,  H04N19/139 ,  H04N19/59 ,  H04N19/70

Abstract: A method and apparatus for decoding data for still or video processing into a bitstream are provided. In particular, two or more sets of feature map elements are obtained from the bitstream. Each set of feature map elements relates to a feature map. Each of the two or more sets of feature map elements is then respectively inputted into two or more feature map processing layers out of a plurality of cascaded layers. The decoded data for picture or video processing is then obtained as a result of the processing by the plurality of cascaded layers. According to the present disclosure, the data may be decoded from the bitstream in an efficient manner in the layered structure.