US 12,079,936 B2
Portrait editing and synthesis
Jiaolong Yang, Redmond, WA (US); Fang Wen, Beijing (CN); Dong Chen, Zhuji (CN); and Xin Tong, Beijing (CN)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Appl. No. 17/615,084
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
PCT Filed Jun. 8, 2020, PCT No. PCT/US2020/036543
§ 371(c)(1), (2) Date Nov. 29, 2021,
PCT Pub. No. WO2020/263541, PCT Pub. Date Dec. 30, 2020.
Claims priority of application No. 201910578770.7 (CN), filed on Jun. 28, 2019.
Prior Publication US 2022/0222897 A1, Jul. 14, 2022
Int. Cl. G06T 19/00 (2011.01); G06T 7/11 (2017.01); G06T 7/50 (2017.01); G06T 11/00 (2006.01); G06T 17/00 (2006.01); G06V 40/16 (2022.01)
CPC G06T 19/00 (2013.01) [G06T 7/11 (2017.01); G06T 7/50 (2017.01); G06T 11/00 (2013.01); G06T 17/00 (2013.01); G06V 40/16 (2022.01); G06T 2200/08 (2013.01); G06T 2207/20021 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/20212 (2013.01); G06T 2207/30201 (2013.01)] 10 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
obtaining a first image about a head of a user;
generating, based on the first image, a three-dimensional head model representing the head of the user which comprises:
determining a face region corresponding to a face of the user in the first image; and
generating, based on the first image, a three-dimensional face model representing a face of the user;
determining a head region uncovered by the three-dimensional face model;
generating, based on the first image and the three-dimensional face model, a first depth map corresponding to the head region uncovered by the three-dimensional face model, wherein generating the first depth map comprises:
generating, based on the three-dimensional face model, a second depth map corresponding to the face region; and
generating, using a third neural network trained in an unsupervised learning manner, the first depth map based on the first image and the second depth map;
generating the three-dimensional head model based on the three-dimensional face model and the first depth map;
in response to receiving a command of changing a head feature of the user, transforming the three-dimensional head model to reflect the changed head feature; and
generating, based on the transformed three-dimensional head model, a second image about the head of the user, the second image reflecting the changed head feature.