公开(公告)号：US20240056575A1

公开(公告)日：2024-02-15

申请号：US18259055

申请日：2021-12-22

Applicant: INTELLECTUAL DISCOVERY CO., LTD.

Inventor： Yongjo AHN ,  Jongseok LEE

IPC: H04N19/124 ,  G06V10/771 ,  G06V10/82

CPC classification number: H04N19/124 ,  G06V10/771 ,  G06V10/82

Abstract: A deep learning-based signal processing method according to the present invention may: obtain a quantized feature map from a bitstream; reconstruct the feature map by performing inverse quantization on the quantized feature map; and synthesize the reconstructed feature map on the basis of a neural network.

公开(公告)号：US20250088632A1

公开(公告)日：2025-03-13

申请号：US18580567

申请日：2022-07-25

Applicant: INTELLECTUAL DISCOVERY CO., LTD.

Inventor： Yongjo AHN ,  Jongseok LEE

IPC: H04N19/124 ,  H04N19/132 ,  H04N19/18

Abstract: A neural network-based image processing method and device according to embodiments of the present invention can: perform preprocessing for an input image; obtain a feature map from the pre-processed image by means of a neural network comprising a plurality of neural network layers; perform quantization for the obtained feature map; and perform video conversion with respect to the quantized feature map.

公开(公告)号：US20230229894A1

公开(公告)日：2023-07-20

申请号：US18002195

申请日：2021-06-25

Applicant: INTELLECTUAL DISCOVERY CO., LTD.

Inventor： Yongjo AHN ,  Jongseok LEE

IPC: G06N3/0495 ,  H04N19/42 ,  G06N3/08

CPC classification number: G06N3/0495 ,  H04N19/42 ,  G06N3/08

Abstract: A neural-network-based signal processing method and apparatus according to the present invention may: receive a bitstream including information about a neural network model, wherein the bitstream includes at least one neural network access unit; obtain information about the at least one neural network access unit from the bitstream; and reconstruct the neural network model on the basis of the information about the at least one neural network access unit.

公开(公告)号：US20250159177A1

公开(公告)日：2025-05-15

申请号：US18839004

申请日：2023-02-17

Applicant: INTELLECTUAL DISCOVERY CO., LTD.

Inventor： Yongjo AHN ,  Jongseok LEE

IPC: H04N19/13 ,  H04N19/119 ,  H04N19/124 ,  H04N19/136 ,  H04N19/176 ,  H04N19/42

Abstract: A neural network-based image processing method and apparatus according to an embodiment of the present invention may: acquire a feature tensor from an input image by using a first neural network including a plurality of neural network layers; acquire a symbol tensor by performing quantization on the acquired feature tensor; and generate a bitstream by performing entropy encoding on the basis of the symbol tensor.

公开(公告)号：US20230421764A1

公开(公告)日：2023-12-28

申请号：US18253381

申请日：2021-11-18

Applicant: INTELLECTUAL DISCOVERY CO., LTD.

Inventor： Yongjo AHN ,  Jongseok LEE

IPC: H04N19/124 ,  G06V10/74 ,  G06V10/764 ,  G06V10/77 ,  G06V10/82 ,  H04N19/136 ,  H04N19/42

CPC classification number: H04N19/124 ,  G06V10/761 ,  G06V10/764 ,  G06V10/7715 ,  G06V10/82 ,  H04N19/136 ,  H04N19/42

Abstract: A neural network-based signal processing method and device according to the present invention generates a feature map by means of a multilayer neural network comprising a plurality of neural networks, and performs quantization for the feature map, the quantization performed on the basis of the structure of the multilayer neural network or the attribute of the feature map.