The paper describes a method for automatically extracting informative feature hierarchies for object classification, and shows the advantage of the features constructed hierarchic...
Lambertian photometric stereo with unknown light source parameters is ambiguous. Provided that the object imaged constitutes a surface, the ambiguity is represented by the group o...
This paper develops new theory for the optimal placement of photometric stereo lighting in the presence of camera noise. We show that for three lights, any triplet of orthogonal l...
The recognition of facial gestures and expressions in image sequences is an important and challenging problem. Most of the existing methods adopt the following paradigm. First, fa...
Occlusion is one of the challenging problems in stereo. In this paper, we solve the problem in a segment-based style. Both images are segmented, and we propose a novel patchbased ...
Classic methods for Bayesian inference effectively constrain search to lie within regions of significant probability of the temporal prior. This is efficient with an accurate dyna...
David Demirdjian, Leonid Taycher, Gregory Shakhnar...
In most cases when information is to be extracted from an image, there are priors available on the state of the world and therefore on the detailed measurements which will be obta...
Nearly all existing methods for stereo reconstruction assume that scene reflectance is Lambertian, and make use of color constancy as a matching invariant. We introduce a new inva...
We present an object recognition algorithm that uses model and image line features to locate complex objects in high clutter environments. Finding correspondences between model an...