Unsupervised Training for 3D Morphable Model Regression
Name
1806.06098.pdf
Description
Accepted version
Size
9.56 MB
Format
Adobe PDF
Checksum (MD5)
6e4e66e6eae0cc61712fb8e8b077ee31
Author(s)
Genova, Kyle
Cole, Forrester
Maschinot, Aaron
Sarna, Aaron
Vlasic, Daniel
Freeman, William T.
Date Issued
June 2018
Publisher
IEEE
Citation
Genova, Kyle, Cole, Forrester, Maschinot, Aaron, Sarna, Aaron, Vlasic, Daniel et al. 2018. "Unsupervised Training for 3D Morphable Model Regression."
Version
Author's final manuscript
Abstract
© 2018 IEEE. We present a method for training a regression network from image pixels to 3D morphable model coordinates using only unlabeled photographs. The training loss is based on features from a facial recognition network, computed on-the-fly by rendering the predicted faces with a differentiable renderer. To make training from features feasible and avoid network fooling effects, we introduce three objectives: A batch distribution loss that encourages the output distribution to match the distribution of the morphable model, a loopback loss that ensures the network can correctly reinterpret its own output, and a multi-view identity loss that compares the features of the predicted 3D face and the input photograph from multiple viewing angles. We train a regression network using these objectives, a set of unlabeled photographs, and the morphable model itself, and demonstrate state-of-the-art results.
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.2018.00874
