In this paper, a generative model based method for recovering both the shape and the reflectance of the surface(s) of a scene from multiple images is presented, assuming that illu...
The estimation of parametric global motion is one of the cornerstones of computer vision. Such schemes are able to estimate various motion models (translation, rotation, affine, p...
We propose a Bayesian framework for representing and recognizing local image motion in terms of two basic models: translational motion and motion boundaries. Motion boundaries are ...
Outdoor face recognition is among the most challenging problems for face recognition. In this paper, we develop a discriminant mutual subspace learning algorithm for indoor and ou...
Intravascular ultrasound images represent a unique tool to analyze the morphology of arteries and vessels (plaques, etc). The poor quality of these images makes traditional segmen...