A network that learns to recognize three-dimensional objects.

TLDR: In this article, a method based on the theory of approximation of multivariate functions is proposed to learn from a small set of perspective views a function mapping any viewpoint to a standard view.

Abstract: THE visual recognition of three-dimensional (3-D) objects on the basis of their shape poses at least two difficult problems. First, there is the problem of variable illumination, which can be addressed by working with relatively stable features such as intensity edges rather than the raw intensity images1,2. Second, there is the problem of the initially unknown pose of the object relative to the viewer. In one approach to this problem, a hypothesis is first made about the viewpoint, then the appearance of a model object from such a viewpoint is computed and compared with the actual image3–7. Such recognition schemes generally employ 3-D models of objects, but the automatic learning of 3-D models is itself a difficult problem8,9. To address this problem in computational vision, we have developed a scheme, based on the theory of approximation of multivariate functions, that learns from a small set of perspective views a function mapping any viewpoint to a standard view. A network equivalent to this scheme will thus 'recognize' the object on which it was trained from any viewpoint.