公开(公告)号：US20240078414A1

公开(公告)日：2024-03-07

申请号：US18507949

申请日：2023-11-13

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Ahmet Burakhan Koyuncu ,  Atanas Boev ,  Elena Alexandrovna Alshina

IPC: G06N3/0464 ,  G06N7/01

CPC classification number: G06N3/0464 ,  G06N7/01

Abstract: Methods and apparatuses are provided for entropy encoding and decoding of a latent tensor, which includes separating the latent tensor into patches and obtaining a probability model for the entropy encoding of a current element of the latent tensor by processing a set of elements from different patches by one or more layers of a neural network. The processing of the set of elements by applying a convolution kernel enables sharing of information between the separated patches.

公开(公告)号：US20240422316A1

公开(公告)日：2024-12-19

申请号：US18818526

申请日：2024-08-28

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Kai Cui ,  Atanas Boev ,  Eckehard Steinbach ,  Elena Alexandrovna Alshina ,  Ahmet Burakhan Koyuncu

IPC: H04N19/12 ,  H04N19/119 ,  H04N19/17 ,  H04N19/33 ,  H04N19/42 ,  H04N19/625 ,  H04N19/63

Abstract: The present disclosure relates to image modification such as an image enhancement wherein the processing is at least partially based on neural networks. In particular, the image modification includes a multi-channel processing in which a primary channel is processed separately and secondary channels are processed based on the processed primary channel. The primary channel is processed based on a first spatial frequency transform to obtain a transformed primary channel and the secondary channel is processed based on a second spatial frequency transform to obtain a transformed secondary channel. The transformed primary channel is processed by means of a first neural network to obtain a modified transformed primary channel and the transformed secondary channel is processed based on the transformed primary channel by means of a second neural network to obtain a modified transformed secondary channel.

公开(公告)号：US20240414361A1

公开(公告)日：2024-12-12

申请号：US18744323

申请日：2024-06-14

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Georgii Petrovich Gaikov ,  Sergey Yurievich Ikonin ,  Ahmet Burakhan Koyuncu ,  Alexander Alexandrovich Karabutov ,  Timofey Mikhailovich Solovyev ,  Elena Alexandrovna Alshina

IPC: H04N19/20 ,  H04N19/17 ,  H04N19/82

Abstract: A method of processing a current object is provided. A set of input data tensors representing the current object are inputted into a first neural layer of a transformer based neural network. Based on information about processing the current object, at least one auxiliary data tensor is inputted into the first neural layer or a second neural layer of the transformer based neural network, where the at least one auxiliary data tensor is different from each of the input data tensors of the set of input data tensors and represents at least one auxiliary input. The set of input data tensors are processed by the transformer based neural network using the at least one auxiliary data tensor in order to obtain a set of output data tensors.

公开(公告)号：US20240244274A1

公开(公告)日：2024-07-18

申请号：US18620667

申请日：2024-03-28

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Ahmet Burakhan Koyuncu ,  Atanas Boev ,  Elena Alexandrovna Alshina

IPC: H04N19/91 ,  G06N7/01 ,  H04N19/436

CPC classification number: H04N19/91 ,  G06N7/01 ,  H04N19/436

Abstract: Methods and apparatuses are described for entropy encoding and decoding of a latent tensor, which includes separating the latent tensor into segments in the spatial dimensions and in the channel dimension, each segment including at least one latent tensor element. An arrangement of the segments is processed by a neural network; the neural network includes at least one attention layer. Based on the processed segment a probability model is obtained for entropy encoding or decoding of a latent tensor element.

公开(公告)号：US20240267568A1

公开(公告)日：2024-08-08

申请号：US18639170

申请日：2024-04-18

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Ahmet Burakhan Koyuncu ,  Han Gao ,  Atanas Boev ,  Elena Alexandrovna Alshina

IPC: H04N19/91 ,  G06V10/44 ,  G06V10/82

CPC classification number: H04N19/91 ,  G06V10/44 ,  G06V10/82

Abstract: Methods and apparatuses are described for entropy encoding and decoding of a latent tensor, which includes separating the latent tensor into segments in the spatial dimensions, each segment including at least one latent tensor element. An arrangement of the segments is processed by a neural network; the neural network includes at least one attention layer. Based on the processed segment a probability model is obtained for entropy encoding or decoding of a latent tensor element.