Recognition systems have generally treated specular highlights as noise. We show how to use these highlights as a positive source of information that improves recognition of shiny...
Margarita Osadchy, David W. Jacobs, Ravi Ramamoort...
The presence of non-symmetric evidence has been a barrier for the application of lifted inference since the evidence destroys the symmetry of the first-order probabilistic model....
Hung B. Bui, Tuyen N. Huynh, Rodrigo de Salvo Braz
We present an unsupervised algorithm for registering 3D surface scans of an object undergoing significant deformations. Our algorithm does not need markers, nor does it assume pri...
This paper presents a probing-based method for probabilistic localization in automated robotic assembly. We consider peg-in-hole problems in which a needle-like peg has a single p...
This paper presents an online learning algorithm to construct from video sequences an image-based representation that is useful for recognition and tracking. For a class of object...