公开(公告)号：US12052418B2

公开(公告)日：2024-07-30

申请号：US17897903

申请日：2022-08-29

Applicant: InterDigital VC Holdings, Inc.

Inventor： Fabrice Leleannec ,  Franck Galpin ,  Fabien Racape ,  Sunil Jaiswal

IPC: H04N19/119 ,  H04N19/102 ,  H04N19/147 ,  H04N19/176 ,  H04N19/70 ,  H04N19/96

CPC classification number: H04N19/119 ,  H04N19/102 ,  H04N19/147 ,  H04N19/176 ,  H04N19/70 ,  H04N19/96

Abstract: A method for encoding a block is disclosed. To this aim, a split mode is determined based on a rate-distortion optimization using a texture-based split prediction set obtained for the block. As an example, the split mode is determined by adapting the texture-based split prediction set according to at least one of a binary or triple split mode non-redundancy constraint or a heuristic-based split mode set pruning. The block is finally encoded using the determined split mode.

公开(公告)号：US20220353502A1

公开(公告)日：2022-11-03

申请号：US17860038

申请日：2022-07-07

Applicant: INTERDIGITAL VC HOLDINGS, INC.

Inventor： Fabrice Le Leannec ,  Franck Galpin ,  Fabien Racape ,  Sunil Jaiswal

IPC: H04N19/119 ,  H04N19/14 ,  H04N19/176

Abstract: A block of video data is split using one or more of several possible partition operations by using the partitioning choices obtained through use of a texture-based image partitioning. In at least one embodiment, the block is split in one or more splitting operations using a convolutional neural network. In another embodiment, inputs to the convolutional neural network come from pixels along the block's causal borders. In another embodiment, boundary information, such as the location of partitions in spatially neighboring blocks, is used by the texture analysis. Methods, apparatus, and signal embodiments are provided for encoding.

公开(公告)号：US20240348781A1

公开(公告)日：2024-10-17

申请号：US18748236

申请日：2024-06-20

Applicant: InterDigital VC Holdings, Inc.

Inventor： Fabrice Leleannec ,  Franck Galpin ,  Fabien Racape ,  Sunil Jaiswal

IPC: H04N19/119 ,  H04N19/102 ,  H04N19/147 ,  H04N19/176 ,  H04N19/70 ,  H04N19/96

CPC classification number: H04N19/119 ,  H04N19/102 ,  H04N19/147 ,  H04N19/176 ,  H04N19/70 ,  H04N19/96

Abstract: A method for encoding a block is disclosed. To this aim, a split mode is determined based on a rate-distortion optimization using a texture-based split prediction set obtained for the block. As an example, the split mode is determined by adapting the texture-based split prediction set according to at least one of a binary or triple split mode non-redundancy constraint or a heuristic-based split mode set pruning. The block is finally encoded using the determined split mode.

公开(公告)号：US11438587B2

公开(公告)日：2022-09-06

申请号：US16772037

申请日：2018-11-07

Applicant: interDigital VC Holdings, Inc.

Inventor： Fabrice Leleannec ,  Franck Galpin ,  Fabien Racape ,  Sunil Jaiswal

IPC: H04N19/119 ,  H04N19/102 ,  H04N19/147 ,  H04N19/176 ,  H04N19/70 ,  H04N19/96

Abstract: A method for encoding a block is disclosed. To this aim, a split mode is determined based on a rate-distortion optimization using a texture-based split prediction set obtained for the block. As an example, the split mode is determined by adapting the texture-based split prediction set according to at least one of a binary or triple split mode non-redundancy constraint or a heuristic-based split mode set pruning. The block is finally encoded using the determined split mode.

公开(公告)号：US11412220B2

公开(公告)日：2022-08-09

申请号：US16771094

申请日：2018-12-12

Applicant: INTERDIGITAL VC HOLDINGS, INC.

Inventor： Fabrice Le Leannec ,  Franck Galpin ,  Fabien Racape ,  Sunil Jaiswal

IPC: H04N19/119 ,  H04N19/14 ,  H04N19/176 ,  H04N19/146

Abstract: A block of video data is split using one or more of several possible partition operations by using the partitioning choices obtained through use of a texture-based image partitioning. In at least one embodiment, the block is split in one or more splitting operations using a convolutional neural network. In another embodiment, inputs to the convolutional neural network come from pixels along the block's causal borders. In another embodiment, boundary information, such as the location of partitions in spatially neighboring blocks, is used by the texture analysis. Methods, apparatus, and signal embodiments are provided for encoding.

公开(公告)号：US20250168338A1

公开(公告)日：2025-05-22

申请号：US19023060

申请日：2025-01-15

Applicant: InterDigital VC Holdings, Inc.

Inventor： Franck Galpin ,  Fabrice LeLeannec ,  Fabien Racape ,  Sunil Jaiswal

IPC: H04N19/119 ,  G06N3/08 ,  H04N19/105 ,  H04N19/176 ,  H04N19/96

Abstract: A block of video data is split using one or more of several possible partition operations by using the partitioning choices obtained through use of a deep learning-based image partitioning. In at least one embodiment, the block is split in one or more splitting operations using a convolutional neural network. In another embodiment, inputs to the convolutional neural network come from pixels along the block's causal borders. In another embodiment, boundary information, such as the location of partitions in spatially neighboring blocks, is used by the convolutional neural network. Methods, apparatus, and signal embodiments are provided for encoding.

公开(公告)号：US12284344B2

公开(公告)日：2025-04-22

申请号：US16771105

申请日：2018-12-12

Applicant: INTERDIGITAL VC HOLDINGS, INC.

Inventor： Fabrice Leleannec ,  Franck Galpin ,  Sunil Jaiswal ,  Fabien Racape

IPC: H04N19/119 ,  G06N3/08 ,  H04N19/105 ,  H04N19/176 ,  H04N19/96

Abstract: A block of video data is split using one or more of several possible partition operations by using the partitioning choices obtained through use of a deep learning-based image partitioning. In at least one embodiment, the block is split in one or more splitting operations using a convolutional neural network. In another embodiment, inputs to the convolutional neural network come from pixels along the block's causal borders. In another embodiment, boundary information, such as the location of partitions in spatially neighboring blocks, is used by the convolutional neural network. Methods, apparatus, and signal embodiments are provided for encoding.

公开(公告)号：US20250039372A1

公开(公告)日：2025-01-30

申请号：US18908728

申请日：2024-10-07

Applicant: InterDigital VC Holdings, Inc.

Inventor： Fabien Racape ,  Fabrice Le Léannec ,  Franck Galpin ,  Sunil Jaiswal

IPC: H04N19/119 ,  H04N19/14 ,  H04N19/146 ,  H04N19/176

Abstract: A block of video data is split using one or more of several possible partition operations by using the partitioning choices obtained through use of a texture-based image partitioning. In at least one embodiment, the block is split in one or more splitting operations using a convolutional neural network. In another embodiment, inputs to the convolutional neural network come from pixels along the block's causal borders. In another embodiment, boundary information, such as the location of partitions in spatially neighboring blocks, is used by the texture analysis. Methods, apparatus, and signal embodiments are provided for encoding.

公开(公告)号：US12155827B2

公开(公告)日：2024-11-26

申请号：US17860038

申请日：2022-07-07

Applicant: INTERDIGITAL VC HOLDINGS, INC.

Inventor： Fabrice Le Leannec ,  Franck Galpin ,  Fabien Racape ,  Sunil Jaiswal

IPC: H04N19/119 ,  H04N19/14 ,  H04N19/146 ,  H04N19/176

Abstract: A block of video data is split using one or more of several possible partition operations by using the partitioning choices obtained through use of a texture-based image partitioning. In at least one embodiment, the block is split in one or more splitting operations using a convolutional neural network. In another embodiment, inputs to the convolutional neural network come from pixels along the block's causal borders. In another embodiment, boundary information, such as the location of partitions in spatially neighboring blocks, is used by the texture analysis. Methods, apparatus, and signal embodiments are provided for encoding.

公开(公告)号：US20220417514A1

公开(公告)日：2022-12-29

申请号：US17897903

申请日：2022-08-29

Applicant: InterDigital VC Holdings, Inc.

Inventor： Fabrice LELEANNEC ,  Franck Galpin ,  Fabien Racape ,  Sunil Jaiswal

IPC: H04N19/119 ,  H04N19/102 ,  H04N19/147 ,  H04N19/176 ,  H04N19/70 ,  H04N19/96

Abstract: A method for encoding a block is disclosed. To this aim, a split mode is determined based on a rate-distortion optimization using a texture-based split prediction set obtained for the block. As an example, the split mode is determined by adapting the texture-based split prediction set according to at least one of a binary or triple split mode non-redundancy constraint or a heuristic-based split mode set pruning. The block is finally encoded using the determined split mode.