US 12,412,599 B2
Image processing method and apparatus, and device and medium
Xinjing Ye, Beijing (CN); Junsheng Wu, Beijing (CN); Haitao Lv, Beijing (CN); and Xi Gao, Beijing (CN)
Assigned to BEIJING ZITIAO NETWORK TECHNOLOGY CO., LTD., Beijing (CN)
Filed by Beijing Zitiao Network Technology Co., Ltd., Beijing (CN)
Filed on Dec. 27, 2022, as Appl. No. 18/089,377.
Application 18/089,377 is a continuation of application No. PCT/CN2022/075622, filed on Feb. 9, 2022.
Claims priority of application No. 202110180571.8 (CN), filed on Feb. 9, 2021.
Prior Publication US 2023/0133416 A1, May 4, 2023
Int. Cl. G11B 27/031 (2006.01); G06T 7/20 (2017.01); G06T 7/70 (2017.01)
CPC G11B 27/031 (2013.01) [G06T 7/20 (2013.01); G06T 7/70 (2017.01); G06T 2207/10016 (2013.01)] 18 Claims
OG exemplary drawing
 
1. An image processing method, comprising:
determining an amount of motion of a first recognition object in an initial video image;
determining a motion state of an effect object according to the amount of motion of the first recognition object, wherein the effect object is an object different from the first recognition object;
if the motion state of the effect object is a first state, synthesizing the effect object with a first styled video image according to the motion state of the effect object, so as to obtain a first target video image; and
if the motion state of the effect object is a second state, synthesizing the effect object with a second styled video image according to the motion state of the effect object, so as to obtain a second target video image;
wherein the first styled video image and the second styled video image are images of different styles that are obtained on the basis of the initial video image,
wherein before the determining the motion state of the effect object according to the amount of motion of the first recognition object, the method further comprises:
selecting, in a template video of the effect object, a target template video image corresponding to the amount of motion of the first recognition object;
wherein the determining the motion state of the effect object according to the amount of motion of the first recognition object comprises:
taking a motion state of the effect object in the target template video image as the motion state of the effect object.