Getting trapped in suboptimal local minima is a perennial problem in model based vision, especially in applications like monocular human body tracking where complex nonlinear para...
We address the automatic recovery of complete 3-D object models from video streams. Usually, complete 3-D models are built by fusing several depth maps, each computed from a small...
A major difficulty for designing a document image segmentation methodology is the proper value selection for all involved parameters. This is usually done after experimentations o...
We show that it is possible to construct numerical models of eye colour from first principles. Our initial model assumes that the important optical interactions occur only in the a...
K. P. B. Cracknell, Damian J. J. Farnell, I. Grier...
In this paper we present a two-level generative model for representing the images and surface depth maps of drapery and clothes. The upper level consists of a number of folds whic...