公开(公告)号：US11330268B2

公开(公告)日：2022-05-10

申请号：US17135427

申请日：2020-12-28

Applicant: Huawei Technologies Co., Ltd.

Inventor： Zhijie Zhao ,  Johannes Sauer ,  Mathias Wien

IPC: H04N19/132 ,  H04N19/105 ,  H04N19/137 ,  H04N19/172 ,  H04N19/46

Abstract: A method for encoding a video signal includes generating an extension region of a first face of a reference frame, where the extension region includes a plurality of extension samples, and a sample value of each extension sample is based on a sample value of a sample of a second face of the reference frame, determining a use of an extension region, providing, based on the use, picture level extension usage information based on the extension region, and encoding the picture level extension usage information into an encoded video signal.

公开(公告)号：US11006147B2

公开(公告)日：2021-05-11

申请号：US16220699

申请日：2018-12-14

Applicant: Huawei Technologies Co., Ltd.

Inventor： Zhijie Zhao ,  Jens Schneider ,  Johannes Sauer ,  Mathias Wien

IPC: H04N19/597 ,  H04N19/176 ,  H04N13/161 ,  H04N13/128 ,  H04N13/111

Abstract: An apparatus for decoding 3D video data is provided, the 3D video data comprising a plurality of texture frames and a plurality of associated depth maps, the apparatus comprising: a first texture decoder configured to decode a video coding block of a first texture frame associated with a first view; a first depth map decoder configured to decode a video coding block of a first depth map associated with the first texture frame; a depth map filter configured to generate an auxiliary depth map on the basis of the first depth map; a first view synthesis prediction unit configured to generate a predicted video coding block of a view synthesis predicted second texture frame associated with a second view on the basis of the video coding block of the first texture frame and the auxiliary depth map.

公开(公告)号：US20250142066A1

公开(公告)日：2025-05-01

申请号：US19007327

申请日：2024-12-31

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Johannes Sauer ,  Panqi Jia ,  Elena Alexandrovna Alshina ,  Atanas Boev

IPC: H04N19/119 ,  H04N19/176 ,  H04N19/186

Abstract: The present disclosure relates to picture encoding and decoding of image regions on tile-basis. In particular, multiple components of an input tensor including a first and second component in spatial dimensions is processed within multiple pipelines. The processing of the first component includes dividing the first component in the spatial dimensions into a first plurality of tiles. Likewise, the processing of the second component includes dividing the second component in the spatial dimensions into a second plurality of tiles. The respective first and second plurality of tiles are then processed each separately. Among the first and second plurality of tiles there are at least two respective collocated tiles differing in size. In case of compression, the processing of the first and/or second component includes picture encoding, rate distortion optimization quantization, and picture filtering. In case of decompression, the processing includes picture decoding and picture filtering.

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：US20250142099A1

公开(公告)日：2025-05-01

申请号：US19007203

申请日：2024-12-31

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Johannes Sauer ,  Panqi Jia ,  Elena Alexandrovna Alshina ,  Atanas Boev

IPC: H04N19/436 ,  H04N19/119 ,  H04N19/172 ,  H04N19/70 ,  H04N19/80 ,  H04N19/85

Abstract: Neural-network-based picture encoding and decoding of image regions may be performed on a tile-basis. An input tensor representing picture data is processed by the neural network, which includes at least a first and second subnetwork. The first subnetwork is applied to a first tensor where the first tensor is divided in a spatial dimensions into a first plurality of tiles. The first tiles are then further processed by the first subnetwork. After application of the first subnetwork, the second subnetwork is applied to a second tensor where the second tensor is divided in the spatial dimensions into a second plurality of tiles. The second tiles are then further processed by the second subnetwork. Among the first and second plurality of tiles there are at least two respective collocated tiles differing in size.

公开(公告)号：US20240296593A1

公开(公告)日：2024-09-05

申请号：US18661245

申请日：2024-05-10

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Alexander Alexandrovich Karabutov ,  Panqi Jia ,  Atanas Boev ,  Han Gao ,  Biao Wang ,  Elena Alexandrovna Alshina ,  Johannes Sauer

IPC: G06T9/00 ,  H04N19/13 ,  H04N19/167 ,  H04N19/186

CPC classification number: G06T9/002 ,  H04N19/13 ,  H04N19/167 ,  H04N19/186

Abstract: A conditional coding of components of an image is described. A method of encoding at least a portion of an image is provided, which comprises encoding a primary component of the image independently from at least one secondary component and encoding the at least one secondary component of the image using information from the primary component. Further, it is provided a method of encoding at least a portion of an image, comprising providing a residual comprising a primary residual component for a primary component of the image and at least one secondary residual component for at least one secondary component of the image that is different from the primary component, encoding the primary residual component independently from the at least one secondary residual component and encoding the at least one secondary residual component using information from the primary residual component.

公开(公告)号：US11838520B2

公开(公告)日：2023-12-05

申请号：US17360805

申请日：2021-06-28

Applicant: Huawei Technologies Co., Ltd.

Inventor： Johannes Sauer ,  Ye-Kui Wang ,  Zhijie Zhao ,  Semih Esenlik

IPC: H04N19/174 ,  H04N19/119 ,  H04N19/172

CPC classification number: H04N19/174 ,  H04N19/119 ,  H04N19/172

Abstract: A device for encoding and a device for decoding a picture, respectively, and corresponding methods relating to the field of picture coding are provided. The devices are respectively configured to partition the picture into one or more slices, each slice comprising one or more tiles, and one or more slices holding coded picture data. Further, the devices are configured to encode the one or more slices holding coded picture data, thereby improving coding and decoding of pictures with uncoded buffer space.

公开(公告)号：US11343504B2

公开(公告)日：2022-05-24

申请号：US17004979

申请日：2020-08-27

Applicant: Huawei Technologies Co., Ltd.

Inventor： Zhijie Zhao ,  Johannes Sauer ,  Mathias Wien

IPC: H04N19/132 ,  H04N19/105 ,  H04N19/117 ,  H04N19/176

Abstract: An apparatus, a method, and a computer program performs image coding with selective loop-filtering. That is, the loop-filters which operate on samples across discontinuous face boundaries are capable of being disabled. The loop-filter operation may be deferred until all samples across a face boundary are known. Then, the loop-filter can use the correct samples according to the 3D arrangement. This may be implemented on the coding block level or at a higher level.

公开(公告)号：US11343488B2

公开(公告)日：2022-05-24

申请号：US16729086

申请日：2019-12-27

Applicant: Huawei Technologies Co., Ltd.

Inventor： Zhijie Zhao ,  Johannes Sauer ,  Mathias Wien

IPC: H04N19/105 ,  H04N19/11 ,  H04N19/176 ,  H04N19/182 ,  H04N19/597 ,  H04N13/161 ,  H04N13/111 ,  H04N13/172 ,  H04N13/282

Abstract: A system for encoding and decoding a video coding block of a multi-view video signal is provided. A decoder is configured to decode a texture-depth video coding block (t0, d0) of a first texture frame and a first depth map associated with a first view for providing a decoded texture-depth video coding block (t0, d0) and the first depth map. A synthesized predicted texture-depth video coding block (tsyn, dsyn) of a view synthesis texture frame and a view synthesis depth map associated with a second view is generated. An inpainted synthesized predicted texture-depth video coding block is generated. Based on the impainted predicted texture-depth video block, the decoder reconstructs a texture-depth video coding block (t1, d1) of a second texture frame and a second depth map associated with the second view. An encoder is configured to encode the texture-depth video coding block in a manner that complements the decoding provided by the decoder.

公开(公告)号：US20210120250A1

公开(公告)日：2021-04-22

申请号：US17135427

申请日：2020-12-28

Applicant: Huawei Technologies Co., Ltd.

Inventor： Zhijie Zhao ,  Johannes Sauer ,  Mathias Wien

IPC: H04N19/132 ,  H04N19/105 ,  H04N19/137 ,  H04N19/46 ,  H04N19/172

Abstract: A method for encoding a video signal includes generating an extension region of a first face of a reference frame, where the extension region includes a plurality of extension samples, and a sample value of each extension sample is based on a sample value of a sample of a second face of the reference frame, determining a use of an extension region, providing, based on the use, picture level extension usage information based on the extension region, and encoding the picture level extension usage information into an encoded video signal.