A robust method for shape-based 3D model retrieval

Abstract

Proliferation of 3D models necessitates developing efficient methods for indexing or retrieving the models in a large database. Many previous methods for this purpose defined functions on concentric spheres as approximation of 3D geometry for spherical harmonic transform (SHT). In this paper, we point out that this is not robust as the surface of a model may shift between different shells under perturbation, and multi-layer of surfaces may exist in one shell, making the function definition ambiguous. To solve these problems, we propose a method to characterize 3D shape using delta functions. Then, spherical functions are defined by sampling in the frequency domain of the delta functions for SHT. By doing so, our method can support retrieval with controllable acuity, which benefits wider range of applications and facilitates customization to different users. Experiments have shown that our method is more robust than previous approaches.