| CPC G06T 19/00 (2013.01) [G06T 7/11 (2017.01); G06T 7/60 (2013.01); G06T 7/74 (2017.01); G06T 17/00 (2013.01); G06V 40/174 (2022.01); G06T 2200/24 (2013.01); G06T 2207/10016 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/20221 (2013.01); G06T 2207/30201 (2013.01)] | 20 Claims |

|
1. A method comprising:
obtaining a to-be-edited image comprising a first face image of a user;
obtaining a first video stream comprising a second face image of the user, wherein the second face image comprises a second facial expression of the user;
editing the first face image based on the second face image to obtain a preliminarily edited image, wherein the preliminarily edited image comprises a third face image of the user;
obtaining a feature image based on the first face image, the third face image, and the second face image, wherein the feature image comprises an eye of the user and an oral cavity of the user; and
fusing the feature image and the third face image to obtain an edited image, wherein the edited image comprises a first facial expression of the user, and wherein the first facial expression is associated with the second facial expression when a mean square error between a first vector that indicates the first facial expression and a second vector that indicates the second facial expression is less than a first threshold.
|