Vision has to deal with uncertainty. The sensors are noisy, the prior knowledge is uncertain
or inaccurate, and the problems of recovering scene information from images are often ill …

The need for error modeling, multisensor fusion, and robust algorithms is becoming
increasingly recognized in computer vision. Bayesian modeling is a powerful, practical, and …

The formulation of the vision problem as a problem in Bayesian inference (Mumford, 1996,
2002; Forsyth and Ponce, 2002) is, by now, well-known and widely accepted in the …

This modern treatment of computer vision focuses on learning and inference in probabilistic
models as a unifying theme. It shows how to use training data to learn the relationships …

Bayesian parameter estimation can be used to generate statistically optimal solutions to the
problem of cue integration. However, the complexity and dimensionality of these solutions is …

We survey the use of Markov models from stochastic geometry as priors in 'high-
level'computer vision, in direct analogy with the use of discrete Markov random fields in 'low …

We describe a learning-based method for low-level vision problems—estimating scenes
from images. We generate a synthetic world of scenes and their corresponding rendered …

Computational vision is a set of inverse problems. We review standard regularization theory,
discuss its limitations, and present new stochastic (in particular, Bayesian) methods for their …

Images are formed as projections of the three-dimensional world onto a two-dimensional
light-sensing surface. The brightness of the image at each point indicates how much light …

Depth perception involves combining multiple, possibly conflicting, sensory measurements
to estimate the 3D structure of the viewed scene. Previous work has shown that the …