/gmm_pointcloud_align

Gaussian Mixture Model

Primary LanguageC++

Point Cloud Alignment with GMM Representation

Exp

Resources

Gaussian Mixture Model

  • GMM Basics Youtube : https://www.youtube.com/playlist?list=PLBv09BD7ez_4e9LtmK626Evn1ion6ynrt

  • Eckart et al. "EOE: Expected Overlap Estimation over Unstructured Point Cloud Data" 3DV 2018

  • Eckart et al. "HGMR: Hierarchical Gaussian Mixtures forAdaptive 3D Registration" ECCV2018

  • Eckart et al. "Accelerated Generative Models for 3D Point Cloud Data" CVPR2016

  • Eckart et al. "Mlmd: Maximum likelihood mixture decoupling for fast andaccurate point cloud registration" 3DV 2015

  • Eckart et al. "EM-Seg: A robust EM algorithmfor parallel segmentation and registration of point clouds" IROS2013

  • Bing & Vemuri "Robust Point Set RegistrationUsing Gaussian Mixture Models" TPAMI 2010

  • Bing & Vemuri "A Robust Algorithm for Point Set Registration Using Mixture of Gaussians" ICCV2005 (conf version of above)

  • Evangelidis et al. "A generative model for the joint registrationof multiple point sets" ECCV2014

  • Horaud et al. "Rigid and articulated point registration with expectation con-ditional maximization" TPAMI2011

  • Straub et al "Efficient Global Point Cloud Alignment using Bayesian Nonparametric Mixtures" CVPR2017

Surfel Mapping

  • SLIC
  • Achanta et al. " SLIC Superpixels Compared to State-of-the-art Superpixel Methods" PAMI'12
  • Kaixuan Wang et al. "Real-time Scalable Dense Surfel Mapping" ICRA2019

PointCloud Alignment

  • Zhou et al. "Learning and Matching Multi-View Descriptors for Registration of Point Clouds" ECCV2018
  • Zhou, Koltun et al "Fast global registration" ECCV16
  • choi, Koltun et al. "Robust Reconstruction of Indoor Scenes" CVPR2015
  • Pomerleau, Siegwart et al "Comparing icp variants onreal-world data sets" AURO2013
  • Yang et al "Go-icp: a globally optimal solution to 3dicp point-set registration" TPAMI2016
  • Briagles et al. " Convex global 3d registration with lagrangianduality." CVPR2017
  • OpenGR: A C++ library for 3D Global Registration, 2017
  • Yue Pan et al. "GH-ICP：Iterative Closest Point algorithm with global optimal matching and hybrid metric" 3DV2018
  • A Comparison of Four Algorithms forEstimating 3-D Rigid Transformations, BMVC1995 (closed form 3d align SVD, 4 algos compared, especially see section 2.1) - Arun et al. "Least-Squares Fitting of Two 3-D PointSets", TPAMI1987 - Horn et al. "Closed-form Solution of AbsoluteOrientation Using Orthonormal Matrices", JOSA1988 - Horn et al. "Closed-form Solution of Absolute Orientation using Unit Quaternions", JOSA87 - Walker "Estimating 3-D Location Parameters UsingDual Number Quaternions", CVGIP1991
  • Park, Q.-Y. Zhou, and V. Koltun, Colored Point Cloud Registration Revisited, ICCV, 2017.
  • Á. P. Bustos and T. J. Chin. Guaranteed outlier removalfor point cloud registration with correspondences (GORE). TMAPI2018,

Pointcloud datasets

Pointcloud 3D Feature Coreespndence

Optical Flow

prefer only fast methods.