Deep, Landmark-Free FAME: Face Alignment, Modeling, and Expression Estimation
Deep, Landmark-Free FAME: Face Alignment, Modeling, and Expression Estimation
Feng-Ju Chang,A. Tran,3 Authors,G. Medioni
2019 · DOI: 10.1007/s11263-019-01151-x
International Journal of Computer Vision · 48 Citations
TLDR
A novel method for modeling 3D face shape, viewpoint, and expression from a single, unconstrained photo is presented and it is shown how accurate landmarks can be obtained as a by-product of the modeling process.