Abstract. We propose and analyze a new vantage point for the learning of mixtures of Gaussians: namely, the PAC-style model of learning probability distributions introduced by Kear...
A dynamical model for retinal processing is presented. The model describes the output of retinal ganglion cells whose receptive field is composed of a center and a surround combi...
In this study, we demonstrate the effectiveness of using extended light sources for modeling the appearance of an object for varying illumination. Extended light sources have a ra...
We develop a Bayesian model of digitized archival films and use this for denoising, or more specifically de-graining, individual frames. In contrast to previous approaches our mod...
Teodor Mihai Moldovan, Stefan Roth, Michael J. Bla...
We present a new technique for the display of high-dynamic-range images, which reduces the contrast while preserving detail. It is based on a two-scale decomposition of the image ...