We present an algorithm for performing Lambertian photometric stereo in the presence of shadows. The algorithm has three novel features. First, a fast graph cuts based method is u...
We present a new algorithm to detect humans in still images utilizing covariance matrices as object descriptors. Since these descriptors do not lie on a vector space, well known m...
This paper proposes a new approach to 3D reconstruction of piecewise planar objects based on two image regularities, connectivity and perspective symmetry. First, we formulate the...
The ability to associate objects across multiple views allows co-operative use of an ensemble cameras for scene understanding. In this paper, we present a principled solution to o...
Conventional mutual information (MI)-based registration using pixel intensities is time-consuming and ignores spatial information, which can lead to misalignment. We propose a met...
We propose a novel MRF-based model for deformable image matching (also known as registration). The deformation is described by a field of discrete variables, representing displace...
Measuring BRDF (Bi-directional Reflectance Distribution Function) requires huge amounts of time because a target object must be illuminated from all incident angles and the reflec...
We describe a method of representing human activities that allows a collection of motions to be queried without examples, using a simple and effective query language. Our approach...
This paper presents a new constraint connecting the signals in multiple views of a surface. The constraint arises from a harmonic analysis of the geometry of the imaging process a...