16 search results - page 4 / 4 » Accurate Face Models from Uncalibrated and Ill-Lit Video Seq... |
FGR
2002
IEEE
13 years 9 months ago
2002
IEEE
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...