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

• URL: http://arxiv.org/abs/2203.09986v1
• Date: Fri, 18 Mar 2022 14:23:49 GMT
• Title: GiNGR: Generalized Iterative Non-Rigid Point Cloud and Surface Registration Using Gaussian Process Regression
• Authors: Dennis Madsen, Jonathan Aellen, Andreas Morel-Forster, Thomas Vetter and Marcel L\"uthi
• Abstract summary: GiNGR builds upon Gaussian Process Morphable Models (GPMM) We show how GPR can warp a reference onto a target, leading to smooth deformations following the prior for any dense, sparse, or partial estimated correspondences. We show how existing algorithms in the GiNGR framework can perform probabilistic registration to obtain a distribution of different registrations.
• Score: 7.072699623549853
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Debiased Batch Normalization via Gaussian Process for Generalizable Person Re-Identification [84.32086702849338]
  Generalizable person re-identification aims to learn a model with only several labeled source domains that can perform well on unseen domains. We propose a novel Debiased Batch Normalization via Gaussian Process approach (GDNorm) for generalizable person re-identification.
  arXiv  Detail & Related papers  (2022-03-03T14:14:51Z)
• Gaussian Processes and Statistical Decision-making in Non-Euclidean Spaces [96.53463532832939]
  We develop techniques for broadening the applicability of Gaussian processes. We introduce a wide class of efficient approximations built from this viewpoint. We develop a collection of Gaussian process models over non-Euclidean spaces.
  arXiv  Detail & Related papers  (2022-02-22T01:42:57Z)
• Non-Gaussian Gaussian Processes for Few-Shot Regression [71.33730039795921]
  We propose an invertible ODE-based mapping that operates on each component of the random variable vectors and shares the parameters across all of them. NGGPs outperform the competing state-of-the-art approaches on a diversified set of benchmarks and applications.
  arXiv  Detail & Related papers  (2021-10-26T10:45:25Z)
• Incremental Ensemble Gaussian Processes [53.3291389385672]
  We propose an incremental ensemble (IE-) GP framework, where an EGP meta-learner employs an it ensemble of GP learners, each having a unique kernel belonging to a prescribed kernel dictionary. With each GP expert leveraging the random feature-based approximation to perform online prediction and model update with it scalability, the EGP meta-learner capitalizes on data-adaptive weights to synthesize the per-expert predictions. The novel IE-GP is generalized to accommodate time-varying functions by modeling structured dynamics at the EGP meta-learner and within each GP learner.
  arXiv  Detail & Related papers  (2021-10-13T15:11:25Z)
• Scalable Variational Gaussian Processes via Harmonic Kernel Decomposition [54.07797071198249]
  We introduce a new scalable variational Gaussian process approximation which provides a high fidelity approximation while retaining general applicability. We demonstrate that, on a range of regression and classification problems, our approach can exploit input space symmetries such as translations and reflections. Notably, our approach achieves state-of-the-art results on CIFAR-10 among pure GP models.
  arXiv  Detail & Related papers  (2021-06-10T18:17:57Z)
• 3DMNDT:3D multi-view registration method based on the normal distributions transform [23.427473819499145]
  This paper proposes a novel multi-view registration method, named 3D multi-view registration based on the normal distributions transform (3DMNDT) The proposed method integrates the K-means clustering and Lie algebra solver to achieve multi-view registration. Experimental results tested on benchmark data sets illustrate that the proposed method can achieve state-of-the-art performance for multi-view registration.
  arXiv  Detail & Related papers  (2021-03-20T03:20:31Z)
• Rigid and Articulated Point Registration with Expectation Conditional Maximization [20.096170794358315]
  We introduce an innovative EM-like algorithm, namely the Conditional Expectation Maximization for Point Registration (ECMPR) algorithm. We analyse in detail the associated consequences in terms of estimation of the registration parameters. We extend rigid registration to articulated registration.
  arXiv  Detail & Related papers  (2020-12-09T17:36:11Z)
• Scalable Gaussian Process Variational Autoencoders [17.345687261000045]
  We propose a new scalable GP-VAE model that outperforms existing approaches in terms of runtime and memory footprint, is easy to implement, and allows for joint end-to-end optimization of all components.
  arXiv  Detail & Related papers  (2020-10-26T10:26:02Z)
• DeepGMR: Learning Latent Gaussian Mixture Models for Registration [113.74060941036664]
  Point cloud registration is a fundamental problem in 3D computer vision, graphics and robotics. In this paper, we introduce Deep Gaussian Mixture Registration (DeepGMR), the first learning-based registration method. Our proposed method shows favorable performance when compared with state-of-the-art geometry-based and learning-based registration methods.
  arXiv  Detail & Related papers  (2020-08-20T17:25:16Z)
• Deformable Groupwise Image Registration using Low-Rank and Sparse Decomposition [0.23310144143158676]
  In this paper, we investigate the drawbacks of the most common RPCA-dissimi-larity metric in image registration. We present a theoretically justified multilevel scheme based on first-order primal-dual optimization to solve the resulting non-parametric registration problem.
  arXiv  Detail & Related papers  (2020-01-10T15:25:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.