Learning Dense Facial Correspondences in Unconstrained Images
ICCV, pp. 4733-4742, 2017.
We present a minimalists but effective neural network that computes dense facial correspondences in highly unconstrained RGB images. Our network learns a per-pixel flow and a matchability mask between 2D input photographs of a person and the projection of a textured 3D face model. To train such a network, we generate a massive dataset of ...More
PPT (Upload PPT)