Deformable 3d shape retrieval using a spectral geometric descriptor

Abstract

In this paper, we propose a deformable 3D shape matching and retrieval approach using a spectral skeleton that encodes nonrigid object structures. This spectral skeleton is constructed from the second eigenfunction of the Laplace-Beltrami operator defined on the surface of a 3D shape, and thus it is invariant to isometric transformations. In addition to its intrinsic property, our proposed shape descriptor is compact, robust to noise, discriminative, and efficient to compute. We also present a graph matching framework by comparing the shortest paths between skeleton endpoints. Extensive experimental results demonstrate the feasibility of the proposed shape retrieval approach on three standard benchmarks of nonrigid 3D shapes.