View-based Shape Similarity using Mutual Information Spheres

Abstract

We present a new method for computing the shape similarity between 3D polygonal models using an informationtheoretic viewpoint selection framework. Given a 3D model, a sphere of viewpoints surrounding this model is used to obtain its shape signature from the mutual information of each viewpoint. This signature represents the essence of the shape from a view-based approach. Then, in order to quantify the dissimilarity between two models, their mutual information spheres are registered by minimizing the L2 distance between them. Several experiments show the discrimination capabilities of our approach and its potential suitability for object recognition.