US 12,249,178 B2
Face reconstruction from a learned embedding
Forrester H. Cole, Cambridge, MA (US); Dilip Krishnan, Arlington, MA (US); William T. Freeman, Acton, MA (US); and David Benjamin Belanger, Cambridge, MA (US)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Filed by Google LLC, Mountain View, CA (US)
Filed on May 16, 2022, as Appl. No. 17/745,158.
Application 17/745,158 is a continuation of application No. 16/857,219, filed on Apr. 24, 2020, granted, now 11,335,120.
Application 16/857,219 is a continuation of application No. 16/061,344, granted, now 10,650,227, issued on May 12, 2020, previously published as PCT/US2017/053681, filed on Sep. 27, 2017.
Claims priority of provisional application 62/414,944, filed on Oct. 31, 2016.
Prior Publication US 2022/0270402 A1, Aug. 25, 2022
Int. Cl. G06V 40/16 (2022.01); G06F 18/214 (2023.01); G06N 20/00 (2019.01); G06T 11/60 (2006.01); G06T 15/02 (2011.01); G06T 17/00 (2006.01); G06V 10/82 (2022.01)
CPC G06V 40/16 (2022.01) [G06F 18/2148 (2023.01); G06N 20/00 (2019.01); G06T 11/60 (2013.01); G06T 15/02 (2013.01); G06T 17/00 (2013.01); G06V 10/82 (2022.01); G06V 40/168 (2022.01); G06T 2210/44 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computing system comprising:
one or more processors;
one or more non-transitory computer readable media that collectively store instructions that, when executed by the one or more processors, cause the computing system to perform operations, the operations comprising:
obtaining an embedding, wherein the embedding was generated by processing an image of a face with a machine-learned image recognition model;
processing the embedding with a machine-learned translation model to generate a plurality of facial modeling parameter values, wherein the plurality of facial modeling parameter values are descriptive of a plurality of facial attributes of the face in the image, and wherein the machine-learned translation model was trained on example embeddings generated from training data comprising a plurality of face morphs, wherein the plurality of face morphs were generated by: processing a plurality of training images to determine a plurality of facial landmarks, determining an average set of facial landmarks, and generating the plurality of face morphs based on warping the plurality of training images to the average set of facial landmarks;
processing the plurality of facial modeling parameter values with a face modeler to generate a model of the face; and
processing the model of the face with a face renderer to generate a rendering of the face.