Three-dimensional model alignment without computing pose
Joseph L. Mundy, Paul M. Payton, Michael H. Brill, Eamon B. Barrett, Richard P. Welty · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 1992
Most current object recognition systems are based on a 3D model which is used to describe the image projection of an object over all viewpoints. We introduce a new technique which can predict the geometry of an object under projective transformation. The object geometry is represented by a set of corresponding features taken from two views. The projected geometry can be constructed in any third view, using a viewpoint invariant derived from the correspondences.