US 12,169,911 B2
Facial image editing and enhancement using a personalized prior
Kfir Aberman, San Mateo, CA (US); Yotam Nitzan, Tel Aviv (IL); Orly Liba, Palo Alto, CA (US); Yael Pritch Knaan, Tel Aviv (IL); Qiurui He, Sunnyvale, CA (US); Inbar Mosseri, Raanana (IL); Yossi Gandelsman, Berkeley, CA (US); and Michal Yarom, Shoham (IL)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Filed by Google LLC, Mountain View, CA (US)
Filed on Jun. 14, 2023, as Appl. No. 18/334,700.
Application 18/334,700 is a continuation of application No. 17/982,842, filed on Nov. 8, 2022, granted, now 11,721,007.
Application 17/982,842 is a continuation of application No. PCT/US2022/011807, filed on Jan. 10, 2022.
Prior Publication US 2023/0325998 A1, Oct. 12, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 5/00 (2024.01); G06T 3/40 (2006.01); G06T 5/50 (2006.01)
CPC G06T 5/50 (2013.01) [G06T 3/40 (2013.01); G06T 5/00 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
for each given image of a set of images of a subject:
generating, by one or more processors, a loss value for each code of a plurality of codes associated with the given image; and
comparing, using the one or more processors, the loss value generated for each code of the plurality of codes to identify an optimized code for the given image having a lowest loss value; and
generating, using the one or more processors, a personalized prior for the subject including each optimized code identified for each given image of the set of images of the subject.