公开(公告)号：US20230377225A1

公开(公告)日：2023-11-23

申请号：US18121444

申请日：2023-03-14

Applicant: Beijing Baidu Netcom Science and Technology Co., Ltd.

Inventor： Chengquan ZHANG ,  Yuechen YU ,  Liang WU

IPC: G06T11/60 ,  G06V20/62 ,  G06V10/82 ,  G06V30/19 ,  G06V30/14

CPC classification number: G06T11/60 ,  G06V20/62 ,  G06V10/82 ,  G06V30/19127 ,  G06V30/1918 ,  G06V30/1444 ,  G06V30/19147 ,  G06V40/10

Abstract: A method for training an image editing model includes steps described below. Covering processing is performed on a region of interest determined in an original image so that a background image sample is formed, and content corresponding to the region of interest is determined as a sample of content of interest; the background image sample and the sample of the content of interest are input into an image editing model; fusion processing is performed on a background image feature and a feature of the region of interest by using the image editing model so that a fusion feature is formed; an image reconstruction operation is performed according to the fusion feature by using the image editing model so that a reconstructed image is output; and optimization training is performed on the image editing model according to a loss relationship between the reconstructed image and the original image.