公开(公告)号：US11830288B2

公开(公告)日：2023-11-28

申请号：US17210827

申请日：2021-03-24

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Kun Yao ,  Zhibin Hong ,  Jieting Xue

IPC: G06F18/214 ,  G06F18/21 ,  G06F18/24 ,  G06F18/2413 ,  G06F18/25 ,  G06V40/16 ,  G06N3/047 ,  G06N20/00 ,  G06T5/50 ,  G06T7/73 ,  G06V10/764 ,  G06V10/774 ,  G06V10/80 ,  G06V10/82 ,  G06N3/088 ,  G06N3/045

CPC classification number: G06V40/169 ,  G06F18/2148 ,  G06F18/2185 ,  G06F18/24765 ,  G06T7/74 ,  G06V10/764 ,  G06V10/774 ,  G06V10/80 ,  G06V10/82 ,  G06V40/168 ,  G06N3/045 ,  G06N3/088 ,  G06T2207/20084 ,  G06T2207/30201

Abstract: Embodiments of the present disclosure provide a method for training a face fusion model and an electronic device. The method includes: performing a first face changing process on a user image and a template image to generate a reference template image; adjusting poses of facial features of the template image based on the reference template image to generate a first input image; performing a second face changing process on the template image to generate a second input image; inputting the first input image and the second input image into a generator of an initial face fusion model to generate a fused face area image; and inputting the fused image and the template image into a discriminator of the initial face fusion model to obtain a result, and performing backpropagation correction on the initial face fusion model based on the result to generate a face fusion model.