Diffeomorphic ICP Registration for Single and Multiple Point Sets

TL;DR

This paper introduces a non-rigid, diffeomorphic extension of the ICP algorithm for point set registration, enabling large deformations and statistical atlas construction, validated on synthetic data.

Contribution

It presents a novel probabilistic formulation of diffeomorphic ICP with a new variation of LDDMM landmark registration, applicable to multiple point sets.

Findings

Successfully validated on synthetic data

Enables large deformation registration

Constructs statistical atlases of point sets

Abstract

We propose a generalization of the iterative closest point (ICP) algorithm for point set registration, in which the registration functions are non-rigid and follow the large deformation diffeomorphic metric mapping (LDDMM) framework. The algorithm is formulated as a well-posed probabilistic inference, and requires to solve a novel variation of LDDMM landmark registration with an additional term involving the Jacobian of the mapping. The algorithm can easily be generalized to construct a diffeomorphic, statistical atlas of multiple point sets. The method is successfully validated on a first set of synthetic data.