公开(公告)号：US11997246B2

公开(公告)日：2024-05-28

申请号：US17721425

申请日：2022-04-15

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Francesca Babiloni ,  Ioannis Marras ,  Ales Leonardis ,  Gregory Slabaugh

IPC: H04N1/64 ,  G06T3/4015

CPC classification number: H04N1/646 ,  G06T3/4015

Abstract: An image processor comprising a plurality of processing modules configured to transform a raw image into an output image. The plurality of processing modules comprise a first module and a second module, each of which implements a respective trained artificial intelligence model. The first module is configured to implement an image transformation operation that recovers luminance from the raw image. The second module is configured to implement an image transformation operation that recovers chrominance from the raw image.

公开(公告)号：US20230410475A1

公开(公告)日：2023-12-21

申请号：US18460319

申请日：2023-09-01

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Francesca Babiloni ,  Ioannis Marras ,  Jiankang Deng ,  Stefanos Zafeiriou

IPC: G06V10/764 ,  G06V10/776 ,  G06V10/82 ,  G06V10/774 ,  G06V10/56

CPC classification number: G06V10/764 ,  G06V10/776 ,  G06V10/56 ,  G06V10/7747 ,  G06V10/82

Abstract: A classification apparatus for allocating a raw image to a respective class out of a plurality of classes, the apparatus comprising one or more processors and a memory storing in non-transient form data defining program code executable by the one or more processors to implement an image classification model, the apparatus being configured to: receive a raw image; generate a plurality of raw matrices from the raw image, wherein each of the plurality of raw matrices is formed by one spatial value and one characteristic value; and allocate the raw image to the respective class depending on the plurality of raw matrices. By forming each of the raw matrices by one spatial value and one characteristic value the computational cost may be reduced.