2020
“Look Ma, no landmarks!” – Unsupervised, Model-based Dense Face Alignment
ECCV 2020poster
no landmarks!"" - Unsupervised, model-based dense face alignment","In this paper, we show how to train an image-to-image network to predict dense correspondence between a face image and a 3D morphable model using only the model for supervision. We show that both geometric parameters (shape, pose and…