Invention Grant
- Patent Title: Face reconstruction from a learned embedding
-
Application No.: US16061344Application Date: 2017-09-27
-
Publication No.: US10650227B2Publication Date: 2020-05-12
- Inventor: Forrester H. Cole , Dilip Krishnan , William T. Freeman , David Benjamin Belanger
- Applicant: Google LLC
- Applicant Address: US CA Mountain View
- Assignee: Google LLC
- Current Assignee: Google LLC
- Current Assignee Address: US CA Mountain View
- Agency: Dority & Manning, P.A.
- International Application: PCT/US2017/053681 WO 20170927
- International Announcement: WO2018/080702 WO 20180503
- Main IPC: G06K9/00
- IPC: G06K9/00 ; G06T11/60 ; G06T15/02 ; G06N20/00 ; G06K9/62 ; G06T17/00

Abstract:
The present disclosure provides systems and methods that perform face reconstruction based on an image of a face. In particular, one example system of the present disclosure combines a machine-learned image recognition model with a face modeler that uses a morphable model of a human's facial appearance. The image recognition model can be a deep learning model that generates an embedding in response to receipt of an image (e.g., an uncontrolled image of a face). The example system can further include a small, lightweight, translation model structurally positioned between the image recognition model and the face modeler. The translation model can be a machine-learned model that is trained to receive the embedding generated by the image recognition model and, in response, output a plurality of facial modeling parameter values usable by the face modeler to generate a model of the face.
Public/Granted literature
- US20190095698A1 Face Reconstruction from a Learned Embedding Public/Granted day:2019-03-28
Information query