We prove that the set of all Lambertian reflectance functions (the mapping from surface normals to intensities) obtained with arbitrary distant light sources lies close to a 9D lin...
This paper presents a method to recover the full-motion (3 rotations and 3 translations) of the head from an input video using a cylindrical head model. Given an initial reference...
Both the configuration of facial features and the timing of facial actions are important to emotion and communication. Previous literature has focused on the former. We developed ...
Jeffrey F. Cohn, Lawrence Ian Reed, Tsuyoshi Moriy...
Head pose estimation from images has recently attracted much attention in computer vision due to its diverse applications in face recognition, driver monitoring and human computer...
Dong Huang, Markus Storer, Fernando DelaTorre, Hor...