Point-Set Registration: Coherent Point Drift
arXiv:0905.2635 · doi:10.1109/TPAMI.2010.46
Abstract
Point set registration is a key component in many computer vision tasks. The goal of point set registration is to assign correspondences between two sets of points and to recover the transformation that maps one point set to the other. Multiple factors, including an unknown non-rigid spatial transformation, large dimensionality of point set, noise and outliers, make the point set registration a challenging problem. We introduce a probabilistic method, called the Coherent Point Drift (CPD) algorithm, for both rigid and non-rigid point set registration. We consider the alignment of two point sets as a probability density estimation problem. We fit the GMM centroids (representing the first point set) to the data (the second point set) by maximizing the likelihood. We force the GMM centroids to move coherently as a group to preserve the topological structure of the point sets. In the rigid case, we impose the coherence constraint by re-parametrization of GMM centroid locations with rigid parameters and derive a closed form solution of the maximization step of the EM algorithm in arbitrary dimensions. In the non-rigid case, we impose the coherence constraint by regularizing the displacement field and using the variational calculus to derive the optimal transformation. We also introduce a fast algorithm that reduces the method computation complexity to linear. We test the CPD algorithm for both rigid and non-rigid transformations in the presence of noise, outliers and missing points, where CPD shows accurate results and outperforms current state-of-the-art methods.
References in corpus (1)
Cited by in corpus (173)
- Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration
- Fast and Robust Iterative Closest Point
- DeepICP: An End-to-End Deep Neural Network for 3D Point Cloud Registration
- A comprehensive survey on point cloud registration
- Blind MultiChannel Identification and Equalization for Dereverberation and Noise Reduction based on Convolutive Transfer Function
- Joint Alignment of Multiple Point Sets with Batch and Incremental Expectation-Maximization
- Building an Aerial-Ground Robotics System for Precision Farming: An Adaptable Solution
- AgriColMap: Aerial-Ground Collaborative 3D Mapping for Precision Farming
- Segmentation of Photovoltaic Module Cells in Uncalibrated Electroluminescence Images
- K-means clustering for efficient and robust registration of multi-view point sets
- A Systematic Approach for Cross-source Point Cloud Registration by Preserving Macro and Micro Structures
- Gromov-Wasserstein Learning for Graph Matching and Node Embedding
- Machine learning enables completely automatic tuning of a quantum device faster than human experts
- Inverse design of deployable origami structures that approximate a general surface
- Semantic Mapping for Orchard Environments by Merging Two-Sides Reconstructions of Tree Rows
- Remote Mobile Manipulation with the Centauro Robot: Full-body Telepresence and Autonomous Operator Assistance
- PointPWC-Net: A Coarse-to-Fine Network for Supervised and Self-Supervised Scene Flow Estimation on 3D Point Clouds
- Unsupervised and Unregistered Hyperspectral Image Super-Resolution with Mutual Dirichlet-Net
- An Adaptive Data Representation for Robust Point-Set Registration and Merging
- Point Cloud Registration for LiDAR and Photogrammetric Data: a Critical Synthesis and Performance Analysis on Classic and Deep Learning Algorithms
- Supervised Autonomous Locomotion and Manipulation for Disaster Response with a Centaur-like Robot
- Shape-aware Surface Reconstruction from Sparse 3D Point-Clouds
- Fast deep learning correspondence for neuron tracking and identification in C.elegans using synthetic training
- Multiway Non-rigid Point Cloud Registration via Learned Functional Map Synchronization
- Occlusion-robust Deformable Object Tracking without Physics Simulation
- Non-iterative rigid 2D/3D point-set registration using semidefinite programming
- GlobalMatch: Registration of Forest Terrestrial Point Clouds by Global Matching of Relative Stem Positions
- Fully automatic integration of dental CBCT images and full-arch intraoral impressions with stitching error correction via individual tooth segmentation and identification
- Scalable Gromov-Wasserstein Learning for Graph Partitioning and Matching
- TEASER: Fast and Certifiable Point Cloud Registration
- 3D Point Cloud Processing and Learning for Autonomous Driving
- PHASER: a Robust and Correspondence-free Global Pointcloud Registration
- Anatomy-aware and acquisition-agnostic joint registration with SynthMorph
- Deformable One-Dimensional Object Detection for Routing and Manipulation
- GMMLoc: Structure Consistent Visual Localization with Gaussian Mixture Models
- Registration of multi-view point sets under the perspective of expectation-maximization
- A Sparse and Locally Coherent Morphable Face Model for Dense Semantic Correspondence Across Heterogeneous 3D Faces
- 3D non-rigid registration using color: Color Coherent Point Drift
- Deep Learning for 3D Point Cloud Understanding: A Survey
- Transferring Category-based Functional Grasping Skills by Latent Space Non-Rigid Registration
- Fast and Accurate Point Cloud Registration using Trees of Gaussian Mixtures
- Discriminative Optimization: Theory and Applications to Computer Vision Problems
- Quaternion-based Unscented Kalman Filter for 6-DoF Vision-based Inertial Navigation in GPS-denied Regions
- Decompose to manipulate: Manipulable Object Synthesis in 3D Medical Images with Structured Image Decomposition
- Multiview Point Cloud Registration Based on Minimum Potential Energy for Free-Form Blade Measurement
- Semantic Context Forests for Learning-Based Knee Cartilage Segmentation in 3D MR Images
- PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency
- DeepGMR: Learning Latent Gaussian Mixture Models for Registration
- Giant Panda Face Recognition Using Small Dataset
- A probabilistic atlas for cell identification
- BARCHAN: Blob Alignment for Robust CHromatographic ANalysis
- A Study on Wrist Identification for Forensic Investigation
- Automatic Robot Hand-Eye Calibration Enabled by Learning-Based 3D Vision
- Fail-Aware LIDAR-Based Odometry for Autonomous Vehicles
- Fast and Globally Optimal Rigid Registration of 3D Point Sets by Transformation Decomposition
- DeepUKF-VIN: Adaptively-tuned Deep Unscented Kalman Filter for 3D Visual-Inertial Navigation based on IMU-Vision-Net
- Anatomically Parameterized Statistical Shape Model: Explaining Morphometry through Statistical Learning
- A Polynomial-time Solution for Robust Registration with Extreme Outlier Rates
- RFVTM: A Recovery and Filtering Vertex Trichotomy Matching for Remote Sensing Image Registration
- milliEgo: Single-chip mmWave Radar Aided Egomotion Estimation via Deep Sensor Fusion
- 3D point cloud registration with shape constraint
- Correspondence Matrices are Underrated
- Homomorphic Sensing
- Bone Surface Reconstruction and Clinical Features Estimation from Sparse Landmarks and Statistical Shape Models: A feasibility study on the femur
- Deep unsupervised 3D human body reconstruction from a sparse set of landmarks
- Automated 2D and 3D Finite Element Overclosure Adjustment and Mesh Morphing Using Generalized Regression Neural Networks
- Fluid Flow Mass Transport for Generative Networks
- Hubless keypoint-based 3D deformable groupwise registration
- Product Manifold Filter: Non-Rigid Shape Correspondence via Kernel Density Estimation in the Product Space
- Shape Registration with Directional Data
- Automatic 3D Registration of Dental CBCT and Face Scan Data using 2D Projection Images
- ANISE: Assembly-based Neural Implicit Surface rEconstruction
- Deformation Recovery: Localized Learning for Detail-Preserving Deformations
- Bayesian Inference of Bijective Non-Rigid Shape Correspondence
- StickyPillars: Robust and Efficient Feature Matching on Point Clouds using Graph Neural Networks
- Multi-view Hybrid Graph Convolutional Network for Volume-to-mesh Reconstruction in Cardiovascular MRI
- SynBench: A Synthetic Benchmark for Non-rigid 3D Point Cloud Registration
- Robust-DefReg: A Robust Deformable Point Cloud Registration Method based on Graph Convolutional Neural Networks
- FilterReg: Robust and Efficient Probabilistic Point-Set Registration using Gaussian Filter and Twist Parameterization
- DeepMapping: Unsupervised Map Estimation From Multiple Point Clouds
- Assembling a RELIC at Redshift 1: Spectroscopic Observations of Galaxies in the RELICS Cluster SPT-CLJ0615-5746
- Hybrid Trilinear and Bilinear Programming for Aligning Partially Overlapping Point Sets
- Coupled Laplacian Eigenmaps for Locally-Aware 3D Rigid Point Cloud Matching
- RetailOpt: Opt-In, Easy-to-Deploy Trajectory Estimation from Smartphone Motion Data and Retail Facility Information
- Multiview Point Cloud Registration via Optimization in an Autoencoder Latent Space
- Hypothesis Testing for Equality of Latent Positions in Random Graphs
- Primitive-based 3D Building Modeling, Sensor Simulation, and Estimation
- Applications of Machine Learning in Document Digitisation
- Introduction to Medical Image Registration with DeepReg, Between Old and New
- The Importance of Being Correlated: Implications of Dependence in Joint Spectral Inference across Multiple Networks
- Fast Gravitational Approach for Rigid Point Set Registration with Ordinary Differential Equations
- Forbidden Region Dynamic Active Constraints in Robot-Assisted Minimally Invasive Surgery
- SMART tracking: Simultaneous anatomical imaging and real-time passive device tracking for MR-guided interventions
- Tracking Partially-Occluded Deformable Objects while Enforcing Geometric Constraints
- Robust Multi-view Registration of Point Sets with Laplacian Mixture Model
- TensorMap: Lidar-Based Topological Mapping and Localization via Tensor Decompositions
- Spline Deformation Field
- Efficient and Deterministic Search Strategy Based on Residual Projections for Point Cloud Registration with Correspondences
- A multi-patient analysis of the center of rotation trajectories using finite element models of the human mandible
- Robust approximate linear regression without correspondence
- 3DMNDT:3D multi-view registration method based on the normal distributions transform
- Multiview point cloud registration with anisotropic and space-varying localization noise
- Agricultural Plant Cataloging and Establishment of a Data Framework from UAV-based Crop Images by Computer Vision
- Provably Approximated ICP
- Efficient Grasp Planning and Execution with Multi-Fingered Hands by Surface Fitting
- Virtual Blood Vessels in Complex Background using Stereo X-ray Images
- Automatic Segmentation of the Prostate on 3D Trans-rectal Ultrasound Images using Statistical Shape Models and Convolutional Neural Networks
- A multi-organ point cloud registration algorithm for abdominal CT registration
- From noisy point clouds to complete ear shapes: unsupervised pipeline
- Quasi-Newton Solver for Robust Non-Rigid Registration
- Automatic clustering of Celtic coins based on 3D point cloud pattern analysis
- Eyes on the Prize: Improved Biological Surface Registration via Forward Propagation
- Laplacian Mixture Model Point Based Registration
- Computer-assisted polyp matching between optical colonoscopy and CT colonography: a phantom study
- Transferring Grasping Skills to Novel Instances by Latent Space Non-Rigid Registration
- Smooth Deformation Field-based Mismatch Removal in Real-time
- Skeleton Extraction from 3D Point Clouds by Decomposing the Object into Parts
- Target-less registration of point clouds: A review
- Dependent landmark drift: robust point set registration with a Gaussian mixture model and a statistical shape model
- TerrainMesh: Metric-Semantic Terrain Reconstruction from Aerial Images Using Joint 2D-3D Learning
- Zero-Assignment Constraint for Graph Matching with Outliers
- A Functional Representation for Graph Matching
- Automatic 3D modelling of craniofacial form
- Topology-Change-Aware Volumetric Fusion for Dynamic Scene Reconstruction
- Non-iterative One-step Solution for Point Set Registration Problem on Pose Estimation without Correspondence
- Robust recognition and exploratory analysis of crystal structures via Bayesian deep learning
- Diffeomorphic ICP Registration for Single and Multiple Point Sets
- Procrustes registration of two-dimensional statistical shape models without correspondences
- Deep Morphing: Detecting bone structures in fluoroscopic X-ray images with prior knowledge
- A Learning-based Optimization Algorithm:Image Registration Optimizer Network
- Regularized Wasserstein Means for Aligning Distributional Data
- Robust Rigid Point Registration based on Convolution of Adaptive Gaussian Mixture Models
- TCM-ICP: Transformation Compatibility Measure for Registering Multiple LIDAR Scans
- Adversarial point set registration
- Learning Parallel Dense Correspondence from Spatio-Temporal Descriptors for Efficient and Robust 4D Reconstruction
- Point Cloud Registration Based on Consistency Evaluation of Rigid Transformation in Parameter Space
- Geometry-Constrained Bidirectional Point Cloud Registration for Thin, Sheet-Like Heritage Artifacts
- Aligning Partially Overlapping Point Sets: an Inner Approximation Algorithm
- Sinkhorn-CPD: Robust point cloud registration via unbalanced entropic optimal transport
- Structured Analytic Mappings for Point Set Registration
- Attention-guided reference point shifting for Gaussian-mixture-based partial point set registration
- Shape-from-Template with Generalised Camera
- Globally optimal point set registration by joint symmetry plane fitting
- The Coherent Point Drift for Clustered Point Sets
- Visual Complexity of Point Set Mappings
- Effective scaling registration approach by imposing the emphasis on the scale factor
- Weighted Motion Averaging for the Registration of Multi-View Range Scans
- Scale Selection of Adaptive Kernel Regression by Joint Saliency Map for Nonrigid Image Registration
- Towards Fine-grained 3D Face Dense Registration: An Optimal Dividing and Diffusing Method
- Real-time multimodal image registration with partial intraoperative point-set data
- Dynamic Formation Reshaping Based on Point Set Registration in a Swarm of Drones
- Robust Ellipsoid-specific Fitting via Expectation Maximization
- A Combinatorial Solution to Non-Rigid 3D Shape-to-Image Matching
- MonoPLFlowNet: Permutohedral Lattice FlowNet for Real-Scale 3D Scene FlowEstimation with Monocular Images
- Average Outward Flux Skeletons for Environment Mapping and Topology Matching
- Registration Loss Learning for Deep Probabilistic Point Set Registration
- Casting graph isomorphism as a point set registration problem using a simplex embedding and sampling
- Unsupervised Word Translation Pairing using Refinement based Point Set Registration
- Effective multi-view registration of point sets based on student's t mixture model
- A Self-Supervised Deep Framework for Reference Bony Shape Estimation in Orthognathic Surgical Planning
- A Robust Loss for Point Cloud Registration
- Probabilistic Registration for Gaussian Process 3D shape modelling in the presence of extensive missing data
- DispVoxNets: Non-Rigid Point Set Alignment with Supervised Learning Proxies
- Uncertainty-Aware Annotation Protocol to Evaluate Deformable Registration Algorithms
- Fast Simultaneous Gravitational Alignment of Multiple Point Sets
- An Improved Discriminative Optimization for 3D Rigid Point Cloud Registration
- Blind Facial Image Quality Enhancement using Non-Rigid Semantic Patches
- Global Point Cloud Registration Network for Large Transformations
- Fast Coherent Point Drift
- Blur Removal via Blurred-Noisy Image Pair
- A Second-Order Lower Bound for Globally Optimal 2D Registration
- Controlling Meshes via Curvature: Spin Transformations for Pose-Invariant Shape Processing
- An Effective Approach for Point Clouds Registration Based on the Hard and Soft Assignments