GiNGR: Generalized Iterative Non-Rigid Point Cloud and Surface Registration Using Gaussian Process Regression

TL;DR

GiNGR unifies and generalizes non-rigid point cloud and surface registration methods using Gaussian process regression, enabling explainability, probabilistic analysis, and flexible prior modeling for improved registration performance.

Contribution

It introduces a unified framework, GiNGR, that combines and explains existing registration methods, allowing probabilistic registration and flexible prior incorporation.

Findings

GiNGR can replicate popular registration algorithms like CPD and ICP.

It enables probabilistic registration to analyze uncertainty.

The framework is modular and publicly available.

Abstract

In this paper, we unify popular non-rigid registration methods for point sets and surfaces under our general framework, GiNGR. GiNGR builds upon Gaussian Process Morphable Models (GPMM) and hence separates modeling the deformation prior from model adaptation for registration. In addition, it provides explainable hyperparameters, multi-resolution registration, trivial inclusion of expert annotation, and the ability to use and combine analytical and statistical deformation priors. But more importantly, the reformulation allows for a direct comparison of registration methods. Instead of using a general solver in the optimization step, we show how Gaussian process regression (GPR) iteratively can warp a reference onto a target, leading to smooth deformations following the prior for any dense, sparse, or partial estimated correspondences in a principled way. We show how the popular CPD and ICP algorithms can be directly explained with GiNGR. Furthermore, we show how existing algorithms in the GiNGR framework can perform probabilistic registration to obtain a distribution of different registrations instead of a single best registration. This can be used to analyze the uncertainty e.g. when registering partial observations. GiNGR is publicly available and fully modular to allow for domain-specific prior construction.