We propose an approach to include contextual features for labeling images, in which each pixel is assigned to one of a finite set of labels. The features are incorporated into a p...
We present a framework for calculating low-dimensional bases to represent image irradiance from surfaces with isotropic reflectance under arbitrary illumination. By representing t...
Abstract. In many vision problems, the observed data lies in a nonlinear manifold in a high-dimensional space. This paper presents a generic modelling scheme to characterize the no...
Ying Zhu, Dorin Comaniciu, Stuart C. Schwartz, Vis...
We describe a framework for decomposing the distortion between two images into a linear combination of components. Unlike conventional linear bases such as those in Fourier or wav...
We propose methods to super-resolve compressed video sequences that may consist of frames with missing blocks of pixels in addition to compression artifacts. Different from tradit...