Robust Consistent Correspondence Between 3D Non-Rigid Shapes Based on "Dual Shape-DNA"

Abstract

In this paper, we propose a novel framework to construct dense and high-quality consistent correspondence between non-rigid surfaces. Our correspondence framework exploits "Dual Shape-DNA" (dual Laplace-Beltrami spectral embedding) to capture global characteristics of objects, and converts two originally different and complex shapes into two similar and simple shapes to facilitate the correspondence. Since our method avoids the computation of geodesic distances, it is robust to local topology changes. By exploiting the excellent properties of the dual domain, our dual spectral framework can robustly construct Laplace-Beltrami embeddings on highly non-regular 3D meshes. After performing initial non-rigid matching in the dual Laplace-Beltrami spectral domain, we return 3D spatial domain and apply a shape-preserving non-rigid deformation to produce the final dense consistent correspondence. We show that our framework is suitable for non-rigid consistent correspondence, and the high-quality correspondence results are achieved.