Non-Rigid Articulated Point Set Registration With Local Structure Preservation

Song Ge, Guoliang Fan; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2015, pp. 126-133

Abstract


We propose a new Gaussian mixture model (GMM)-based probabilistic point set registration method, called Local Structure Preservation (LSP), which is aimed at complex non-rigid and articulated deformations. LSP integrates two complementary shape descriptors to preserve the local structure. The first one is the Local Linear Embedding (LLE)-based topology constraint to retain the local neighborhood relationship, and the other is the Laplacian Coordinate (LC)-based energy to encode the local neighborhood scale. The registration is formulated as a density estimation problem where the LLE and LC terms are embedded in the GMM-based Coherent Point Drift (CPD) framework. A closed form solution is solved by an Expectation Maximization (EM) algorithm where the two local terms are jointly optimized along with the CPD coherence constraint. The experimental results on a challenging 3D human dataset show the accuracy and efficiency of our proposed approach to handle non-rigid highly articulated deformations.

Related Material


[pdf]
[bibtex]
@InProceedings{Ge_2015_CVPR_Workshops,
author = {Ge, Song and Fan, Guoliang},
title = {Non-Rigid Articulated Point Set Registration With Local Structure Preservation},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2015}
}