In this work we apply Convolutional Neural Networks (CNNs) on the challenging task of both 2D and 3D face recognition. We constructed two CNN models, namely CNN-1 (two convolutional layers) and CNN-2 ...

The display consists of multiple screens that present remote participants' faces so as to show their gaze direction, i.e., the direction in which they are looking. We introduce a prototype video ...

For the latest release MiDaS 3.1, a technical report and video are available. MiDaS was trained on up to 12 datasets (ReDWeb, DIML, Movies, MegaDepth, WSVD, TartanAir, HRWSI, ApolloScape, BlendedMVS, ...