Classical models for motion detection with artificial neural networks are inspired in physiological data of simple visual systems. Local speed estimationis a problem that involves...
Francisco J. Vico, F. J. Garrido, Francisco Sandov...
In this paper we propose a new framework for modeling 2D shapes. A shape is first described by a sequence of local features (e.g., curvature) of the shape boundary. The resulting ...
We advocate the use of Gaussian Process Dynamical Models (GPDMs) for learning human pose and motion priors for 3D people tracking. A GPDM provides a lowdimensional embedding of hu...
We describe a new vector-based primitive for creating smoothshaded images, called the diffusion curve. A diffusion curve partitions the space through which it is drawn, defining d...
We present a method for automatically rendering pen-and-ink illustrations of trees. A given 3-d tree model is illustrated by the tree and a visual representation of the foliage us...