Non-rigid registration under anisotropic deformations

• DOI: 10.1016/j.cagd.2019.04.014
• Publication Date: 2019-04-05T16:25:15Z
• Authors: Roberto M. Dyke; Yu-Kun Lai; Paul L. Rosin; Gary K.L. Tam
• Keywords: Geometry processing

Non-rigid registration of deformed 3D shapes is a challenging and fundamental task in geometric processing, which aims to non-rigidly deform source shape into alignment with target shape. Current state-of-the-art methods assume deformations be near-isometric. This assumption does not reflect real-world conditions, for example large-scale deformation, where moderate anisotropic (e.g., stretches) are common. In this paper we propose two significant changes typical pipeline address such deformations. First, introduce method estimate non-isometric incorporate an iterative non-rigid pipeline. Second, compute additional correspondences non-isometrically deforming regions using reliable as landmarks prune inconsistent correspondences. We compare the performance our proposed algorithm several existing benchmarks. Experimental results show that outperforms methods.