Synthesizing Normalized Faces from Facial Identity Features
Name
1701.04851.pdf
Description
Accepted version
Size
5.21 MB
Format
Adobe PDF
Checksum (MD5)
5d0ced7b889c9fefa78c8bdc6ffdf9ec
Author(s)
Cole, Forrester
Belanger, David
Krishnan, Dilip
Sarna, Aaron
Mosseri, Inbar
Freeman, William T.
Date Issued
July 2017
Publisher
IEEE
Citation
Cole, Forrester, Belanger, David, Krishnan, Dilip, Sarna, Aaron, Mosseri, Inbar et al. 2017. "Synthesizing Normalized Faces from Facial Identity Features."
Version
Author's final manuscript
Abstract
© 2017 IEEE. We present a method for synthesizing a frontal, neutralexpression image of a person's face given an input face photograph. This is achieved by learning to generate facial landmarks and textures from features extracted from a facial-recognition network. Unlike previous generative approaches, our encoding feature vector is largely invariant to lighting, pose, and facial expression. Exploiting this invariance, we train our decoder network using only frontal, neutral-expression photographs. Since these photographs are well aligned, we can decompose them into a sparse set of landmark points and aligned texture maps. The decoder then predicts landmarks and textures independently and combines them using a differentiable image warping operation. The resulting images can be used for a number of applications, such as analyzing facial attributes, exposure and white balance adjustment, or creating a 3-D avatar.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/cvpr.2017.361
