Computing 3D object parts from similarities among object views

The following shape segmentation problem is addressed: find the part decomposition of a 3D object that accounts for an observed pattern of similarities among several of the object´s views. This represents the inverse, ill-posed version of the direct problem of computing perceptual similarities among object views when the object parts are known. The problem is solved by inverting a proposed model for the direct similarity-from-parts problem by resorting to regularization techniques. The algorithm takes as input the geometry of the object (given as a triangular mesh), the camera positions corresponding to the rest views, and the perceptual similarities among the test views. The output of the algorithm is a segmentation of the surface of the object into connected regions, i.e., parts