no code implementations • 4 Jun 2019 • Robert Wagner, Daniel Crispell, Patrick Feeney, Joe Mundy
Designing robust activity detectors for fixed camera surveillance video requires knowledge of the 3-D scene.
no code implementations • 29 Aug 2017 • Daniel Crispell, Maxim Bazik
An efficient, fully automatic method for 3D face shape and pose estimation in unconstrained 2D imagery is presented.
no code implementations • 17 Aug 2017 • Maxim Bazik, Daniel Crispell
Commercial off the shelf (COTS) 3D scanners are capable of generating point clouds covering visible portions of a face with sub-millimeter accuracy at close range, but lack the coverage and specialized anatomic registration provided by more expensive 3D facial scanners.
no code implementations • 14 Apr 2017 • Daniel Crispell, Octavian Biris, Nate Crosswhite, Jeffrey Byrne, Joseph L. Mundy
The performance of modern face recognition systems is a function of the dataset on which they are trained.