The biological visual system possesses the ability to compute layered surface representations, in which one surface is represented as being viewed through another. This ability is...
We introduce a new structural constraint that can be used for matching points in image pairs taken from a wide baseline. No assumption is made about the geometry of the 3?D points...
We present a novel stereo vision modeling framework that generates approximate, yet physically-plausible representations of objects rather than creating accurate models that are c...
Krishnanand N. Kaipa, Josh C. Bongard, Andrew N. M...
We consider the problem of shape recovery for real world scenes, where a variety of global illumination (interreflections, subsurface scattering, etc.) and illumination defocus e...
Abstract. It is argued that the ability to generalise is the most important characteristic of learning and that generalisation may be achieved only if pattern recognition systems l...