公开(公告)号：US12159373B2

公开(公告)日：2024-12-03

申请号：US17934697

申请日：2022-09-23

Applicant: Huawei Technologies Co., Ltd.

Inventor： Weihang Shao ,  Yinting Wang ,  Yifan Zhang ,  Liping Zhang

IPC: G06T5/50 ,  G06T5/70 ,  G06T5/92 ,  H04N9/64 ,  H04N23/71 ,  H04N23/72 ,  H04N23/90

Abstract: This application discloses an image processing method and apparatus, and relates to the field of image processing technologies, to help optimize a color, a contrast, or a dynamic range of an image, so that an optimized image can be more objective, and robustness is improved. The method is applied to a terminal including a first camera and a second camera. The method includes: when an ISO of the first camera in a current photographing environment is greater than a first threshold, capturing a first image for a first scenario in the current photographing environment; capturing a second image for the first scenario; and optimizing the first image based on the second image to obtain a third image. An image style of the second image is better than that of the first image.

公开(公告)号：US20220207680A1

公开(公告)日：2022-06-30

申请号：US17698698

申请日：2022-03-18

Applicant: Huawei Technologies Co., Ltd.

Inventor： Yinting Wang ,  Xi Zhang ,  Ruihua Li ,  Liping Zhang ,  Yining Huang ,  Yi Lei ,  Zuquan Zheng ,  Yifan Zhang ,  Xin Li ,  Xiaowei Yang

IPC: G06T5/50 ,  G06T3/40 ,  G06T5/00

Abstract: An image processing method includes obtaining a plurality of frames of raw images. After preprocessing such as image alignment, channel splitting or pixel rearrangement is performed on the obtained plurality of frames of raw images, detail restoration is performed on an image based on a deep learning network, and luminance enhancement and color enhancement are performed on an image output by the deep learning network. A plurality of types of processing related to detail restoration are integrated into a same deep learning network.