US 12,340,474 B2
Image effect implementing method and apparatus, electronic device and storage medium
Jingcong Zhang, Los Angeles, CA (US); Yunzhu Li, Los Angeles, CA (US); Haoze Li, Los Angeles, CA (US); Zhili Chen, Los Angeles, CA (US); Linjie Luo, Los Angeles, CA (US); Jing Liu, Los Angeles, CA (US); Xiao Yang, Los Angeles, CA (US); Guohui Wang, Los Angeles, CA (US); Jianchao Yang, Los Angeles, CA (US); and Xuchen Song, Los Angeles, CA (US)
Assigned to BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD., Beijing (CN); and BYTEDANCE INC., Los Angeles, CA (US)
Appl. No. 18/004,810
Filed by Beijing Bytedance Network Technology Co., Ltd., Beijing (CN); and BYTEDANCE INC., Los Angeles, CA (US)
PCT Filed Jun. 22, 2021, PCT No. PCT/CN2021/101653
§ 371(c)(1), (2) Date Jan. 9, 2023,
PCT Pub. No. WO2022/007627, PCT Pub. Date Jan. 13, 2022.
Claims priority of application No. 202010663931.5 (CN), filed on Jul. 10, 2020.
Prior Publication US 2023/0245398 A1, Aug. 3, 2023
Int. Cl. G06T 19/00 (2011.01); G06F 3/04815 (2022.01); G06T 7/246 (2017.01); G06T 19/20 (2011.01)
CPC G06T 19/006 (2013.01) [G06F 3/04815 (2013.01); G06T 7/251 (2017.01); G06T 19/20 (2013.01); G06T 2200/24 (2013.01); G06T 2219/2016 (2013.01); G06T 2219/2021 (2013.01)] 16 Claims
OG exemplary drawing
 
1. An image effect implementing method, comprising:
acquiring a first image, recognizing a set object in the first image, and acquiring an augmented reality model corresponding to the set object, wherein the first image is an image of a real world captured by a camera of an electronic device and the augmented reality model is a three dimensional model established for the set object in the real world in advance;
superimposing, according to coordinate information of pixels of the set object, the augmented reality model onto the first image to obtain a second image; and
upon detection of a preset deformation event, controlling, according to a set deformation policy, at least one sub-model of the augmented reality model corresponding to the set object in the second image to deform, and displaying the deformed second image,
wherein different preset conditions trigger different preset deformation events, and the preset deformation event is indicative of deforming the at least one sub-model of the augmented reality model according to the set deformation policy corresponding to the preset deformation event, and
wherein the superimposing, according to the coordinate information of the pixels of the set object, the augmented reality model onto the first image to obtain the second image comprises:
determining, according to the coordinate information of the pixels of the set object, contour coordinates of the set object;
determining, according to the contour coordinates, contour information of the set object, and performing scaling adjustment on the augmented reality model corresponding to the set object according to the contour information; and
covering or replacing the set object with the adjusted augmented reality model corresponding to the set object according to the contour coordinates to obtain the second image.