公开(公告)号：US20240015314A1

公开(公告)日：2024-01-11

申请号：US18338092

申请日：2023-06-20

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Elena Alexandrovna Alshina ,  Han Gao ,  Semih Esenlik

IPC: H04N19/30 ,  H04N19/42

CPC classification number: H04N19/30 ,  H04N19/42

Abstract: Disclosed herein are methods and systems for encoding a picture and decoding a bitstream that may represent an encoded picture. During encoding and decoding, rescaling operations are applied to rescale an input to a size that can be processed by a layer of a neural network. Embodiments disclosed herein provide methods for rescaling that achieve a reduced size of the bitstream, thereby improving compression.

公开(公告)号：US20240013446A1

公开(公告)日：2024-01-11

申请号：US18338105

申请日：2023-06-20

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Elena Alexandrovna Alshina ,  Han Gao ,  Semih Esenlik

IPC: G06T9/00 ,  G06T3/40

CPC classification number: G06T9/002 ,  G06T3/4046

Abstract: A method for encoding a picture and decoding a bitstream that represents a picture using a neural network (NN) that comprises a plurality of sub-networks is provided. The method includes applying, before processing an input with the at least one sub-network comprising at least two downsampling layers, a rescaling to the input, wherein the rescaling comprises changing the size S1 in the at least one dimension to be S1 so that S1 is an integer multiple of a combined downsampling ratio Rk of the at least one sub-network, after the rescaling, processing the input by the at least one sub-network comprising at least two downsampling layers and providing an output with the size S2, wherein S2 is smaller than S1, and providing, after processing the picture using the NN, a bitstream as output.

公开(公告)号：US20230412807A1

公开(公告)日：2023-12-21

申请号：US18459110

申请日：2023-08-31

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Alexander Alexandrovich Karabutov ,  Saeed Ranjbar Alvar ,  Ivan Bajic ,  Hyomin Choi ,  Robert A. Cohen ,  Sergey Yurievich Ikonin ,  Timofey Mikhailovich Solovyev ,  Elena Alexandrovna Alshina

IPC: H04N19/124 ,  H04N19/37 ,  G06N3/042

CPC classification number: H04N19/124 ,  H04N19/37 ,  G06N3/042

Abstract: Methods and apparatuses for compression of feature tensors of a neural network are provided. One or more encoding parameters for encoding the channels of a feature tensor are selected according to the importance of the channels. This enables unequal bit allocation according to the importance. Furthermore, the deployed neural network may be trained or fine-tuned considering the effect of encoding noise applied to the intermediate feature tensors. According to the present disclosure, the encoding and modified training methods are advantageous at least for employment in a collaborative intelligence framework.

公开(公告)号：US20230336784A1

公开(公告)日：2023-10-19

申请号：US18336735

申请日：2023-06-16

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Semih Esenlik ,  Panqi Jia ,  Elena Alexandrovna Alshina

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

CPC classification number: 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：US11792410B2

公开(公告)日：2023-10-17

申请号：US17827144

申请日：2022-05-27

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

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

IPC: H04N19/105 ,  H04N19/176 ,  H04N19/159 ,  H04N19/196

CPC classification number: H04N19/159 ,  H04N19/105 ,  H04N19/176 ,  H04N19/197

Abstract: A method of coding implemented by a decoding device or an encoding device, comprising obtaining indication information for a luma position (cbWidth/2, cbHeight/2) of a current coding block, relative to a top-left luma sample position (xCb, yCb) of the current coding block; setting a value of a luma intra prediction mode associated with the current coding block to a first default value, when the indication information indicates that an Intra Block Copy (IBC) mode or palette mode is applied for the luma component at the luma position (cbWidth/2, cbHeight/2), relative to the top-left luma sample position (xCb, yCb) of the current coding block; and obtaining a value of a chroma intra prediction mode based on the value of the luma intra prediction mode of the current coding block.

公开(公告)号：US11765383B2

公开(公告)日：2023-09-19

申请号：US17237924

申请日：2021-04-22

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Timofey Mikhailovich Solovyev ,  Roman Igorevich Chernyak ,  Alexander Alexandrovich Karabutov ,  Jianle Chen ,  Sergey Yurievich Ikonin ,  Elena Alexandrovna Alshina

IPC: H04N19/573 ,  H04N19/159 ,  H04N19/176 ,  H04N19/577

CPC classification number: H04N19/573 ,  H04N19/159 ,  H04N19/176 ,  H04N19/577

Abstract: The present disclosure relates to video encoding and decoding, and in particular to determining motion information for a current block using a history-based motion vector predictor, HMVP, list. The HMVP list is constructed, with said list being an ordered list of N HMVP candidates Hk, k=0, . . . , N−1, which are associated with motion information of N preceding blocks of the frame and precede the current block. Each HMVP candidate has motion information including elements of one or more motion vectors, MVs, one or more reference picture indices corresponding to the MVs, and one or more bi-prediction weight indices. One or more HMVP candidates from the HMVP list are added into a motion information candidate list for the current block; and the motion information is derived based on the motion information candidate list.

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：US11616980B2

公开(公告)日：2023-03-28

申请号：US17478621

申请日：2021-09-17

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

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

IPC: H04N19/593 ,  H04N19/105 ,  H04N19/132 ,  H04N19/172 ,  H04N19/176

Abstract: A method of coding implemented is provided. The method includes the following operations: obtained the height and width of a prediction block without applying clipping operation; calculating a value of a vertical component of an intra prediction sample based on the height and width of the prediction block; calculating a value of a horizontal component of the intra prediction sample based on the height and width of the prediction block; and generating the intra prediction sample based on the value of the vertical component and the value of the horizon component.

公开(公告)号：US20230076920A1

公开(公告)日：2023-03-09

申请号：US17987723

申请日：2022-11-15

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Hu Chen ,  Lars Hertel ,  Erhardt Barth ,  Thomas Martinetz ,  Elena Alexandrovna Alshina ,  Anand Meher Kotra ,  Nicola GIULIANI

IPC: G06T5/00 ,  G06T3/40 ,  G06N3/08 ,  G06N3/04

Abstract: The present disclosure relates to image processing and in particular to modification of an image using a processing such as neural network. The processing is performed to generate a correction image based on an input image. Then, the input image is modified by combining it with the correction image. The processing with the neural network includes at least one stage including image down-sampling and filtering of the down-sampled image; and at least one stage of image up-sampling. An advantage of such approach is increased efficiency of the neural network, which may lead to faster learning and improved performance. The embodiments provide methods and apparatuses for the processing with a trained neural network, as well as methods and apparatuses for training of such neural network for image modification.

公开(公告)号：US20230074457A1

公开(公告)日：2023-03-09

申请号：US17976685

申请日：2022-10-28

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Alexey Konstantinovich FILIPPOV ,  Vasily Alexeevich RUFITSKIY ,  Elena Alexandrovna Alshina

IPC: H04N19/82 ,  H04N19/59

Abstract: Intra- or inter-prediction can be used for video encoding and decoding. For that purpose, an apparatus and methods obtain a filter (a set of coefficients) from a set of filters based on the subsample position (p) defined for the set of positions of predicted samples, where the set of filters is obtained by combining at least two pre-defined input filter sets.