- Feature preserving non-rigid iterative weighted closest point and semi-curvature registration. TIP. 2022
- Accurate Point Cloud Registration with Robust Optimal Transport. NIPS. 2021
- Quasi-Newton Solver for Robust Non-Rigid Registration. CVPR 2020.
- Efficient Second-Order Plane Adjustment. CVPR 2023
- Robust Multiview Point Cloud Registration With Reliable Pose Graph Initialization and History Reweighting. CVPR2023
- Large-Scale LiDAR Consistent Mapping Using Hierarchical LiDAR Bundle Adjustment. ICRL 2023
- On Bundle Adjustment for Multiview Point Cloud Registration. ICRL 2021
- BALM: Bundle Adjustment for Lidar Mapping. ICRL 2021
- Learning multiview 3D point cloud registration. CVPR 2020.
- DMS: Low-overlap Registration of 3D Point Clouds with Double-layer Multi-scale Star-graph. TVCG 2024
- Deep Semantic Graph Matching for Large-Scale Outdoor Point Cloud Registration TGRS 2024
- PointDifformer: Robust Point Cloud Registration With Neural Diffusion and Transformer. TGRS 2024
- Unsupervised Deep Probabilistic Approach for Partial Point Cloud Registration. CVPR 2023
- GeoTransformer: Fast and Robust Point Cloud Registration With Geometric Transformer. TPAMI 2023
- Correspondence-Free Point Cloud Registration with SO(3)-Equivariant Implicit Shape Representations. PMLR 2022.
- PREDATOR: Registration of 3D Point Clouds with Low Overlap. CVPR2021
- RPM-Net: Robust Point Matching using Learned Features. CVPR2020
- Robust Point Cloud Registration Framework Based on Deep Graph Matching. CVPR2021
- PointDSC: Robust Point Cloud Registration Using Deep Spatial Consistency. CVPR2021
- UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Rendering. CVPR2021
- End-to-End Learning Local Multi-view Descriptors for 3D Point Clouds. CVPR2020
- Riga: Rotation-invariant and globally-aware descriptors for point cloud registration. TPAMI 2024
- RoReg: Pairwise Point Cloud Registration With Oriented Descriptors and Local Rotations. TPAMI 2023
- BUFFER: Balancing Accuracy, Efficiency, and Generalizability in Point Cloud Registration. CVPR 2023
- SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration. CVPR2021
- (MeshDOG)Keypoints and Local Descriptors of Scalar Functions on 2D Manifolds. IJCV 2012
- Scale-invariant features for 3-D mesh models." TIP 2012
- On the Repeatability and Quality of Keypoints for Local Feature-based 3D Object Retrieval from Cluttered Scenes. IJCV 2009.
- DICP: Doppler Iterative Closest Point Algorithm. arxiv 2022
- Stein ICP for Uncertainty Estimation in Point Cloud Matching. ICRA. 2022
- Sparse point cloud registration and aggregation with mesh‐based generalized iterative closest point. 2021
- Registration of 3D Point Sets Using Correntropy Similarity Matrix. 2021
- Provably Approximated Point Cloud Registration. ICCV'2021
- Scale-Adaptive ICP. PR. 2021.
- LSG-CPD: Coherent Point Drift with Local Surface Geometry for Point Cloud Registration. ICCV'2021
- Fast and Robust Iterative Closest Point. TPAMI 2021
- Estimating Motion Uncertainty with Bayesian ICP. ICRA. 2020
- Analysis of robust functions for registration algorithms.ICRA 2019.
- FilterReg: Robust and Efficient Probabilistic Point-Set Registration using Gaussian Filter and Twist Parameterization. CVPR'2019
- Analysis of Robust Functions for Registration Algorithms. ICRA 2019.
- Quality-based registration refinement of airborne LiDAR and photogrammetric point clouds.ISPRS 2019
- A symmetric objective function for ICP."ACM Transactions on Graphics. TOG 2019
- Effective scaling registration approach by imposing the emphasis on the scale factor. 2019
- Correntropy based scale ICP algorithm for robust point set registration. 2019
- https://opals.geo.tuwien.ac.at/html/stable/ModuleStripAdjust.html
- CICP: Cluster Iterative Closest Point for sparse–dense point cloud registration. 2018 RAS.
- AA-ICP: Iterative closest point with Anderson acceleration.ICRA, 2018.
- Multi-Channel Generalized-ICP: A robust framework for multi-channel scan registration. 2017. RAS
- GOGMA: Globally-Optimal Gaussian Mixture Alignment. 2016 CVPR.
- A GMM based uncertainty model for point clouds registration. 2016. RAS
- Multi channel generalized-ICP. ICRA, 2014.
- Sparse iterative closest point. CGF 2013
- Toward mutual information based automatic registration of 3D point clouds. 2012 ICIRS
- Point set registration: Coherent point drift. TPAMI 2010
- [GMMReg]Robust point set registration using gaussian mixture models. TPAMI 2011.
- A scale stretch method based on ICP for 3D data registration. 2009
- [KC] A correlation-based approach to robust point set registration." ECCV 2004.
- [Hiearchical ICP] A multi-resolution ICP with heuristic closest point search for fast and robust 3D registration of range images. 2003
- The normal distributions transform: A new approach to laser scan matching. IROS 2003
- ICP registration using invariant features. TPAMI 2002.
- Multi-scale EM-ICP: A Fast and Robust Approach for Surface Registration. ECCV 2002.
- Efficient variants of the ICP algorithm. IC3DIM 2001
- Object modelling by registration of multiple range images. IVC 1992
- Method for registration of 3-D shapes. ICOP 1992.
-
Incremental registration towards large-scale heterogeneous point clouds by hierarchical graph matching. ISPRS 2024.
-
Quatro++: Robust global registration exploiting ground segmentation for loop closing in LiDAR SLAM. IJRR 2024
-
Fast Semantic-Assisted Outlier Removal for Large-scale Point Cloud Registration. arxiv'2022
-
[Line] Using 2-Lines Congruent Sets for Coarse Registration of Terrestrial Point Clouds in Urban Scenes. TGRS 2022.
-
Robust global registration of point clouds by closed-form solution in the frequency domain. ISPRS Journal. 2021
-
Object-based incremental registration of terrestrial point clouds in an urban environment. ISPRSJ 2020.
-
[Line] Fast and Automatic Registration of Terrestrial Point Clouds Using 2D Line Features. RS 2020.
-
[4plane PCS] 4-Plane congruent sets for automatic registration of as-is 3D point clouds with 3D BIM models. 2018
-
[V4PCS] V4PCS: Volumetric 4PCS algorithm for global registration. 2017
-
[Plane2Plane] Efficient and Accurate Registration of Point Clouds With Plane to Plane Correspondences. ICCV 2017
-
[Line] Line-Based Registration of Panoramic Images and LiDAR Point Clouds for Mobile Mapping. Sensors 2017.
-
[Outline] An automated method to register airborne and terrestrial laser scanning point clouds. ISPRSJ 2015.
-
Go-ICP. TPAMI 2016
-
[Scale 4PCS]Fully Automatic Registration of Image Sets on Approximate Geometry. IJCV 2013
-
Robust global registration." SGP 2005.
-
Least-Squares Fitting of Two 3-D Point Sets. TPAMI 1987
-
Closed-form solution of absolute orientation using unit quaternions. JOSA 1987
- PCR-99: A Practical Method for Point Cloud Registration with 99% Outliers. ARXIV 2024
- 3D registration with maximal cliques. CVPR 2023
- QGORE: Quadratic-Time Guaranteed Outlier Removal for Point Cloud Registration. TPAMI 2023
- Accurate Registration of Cross-Modality Geometry via Consistent Clustering. TVCG 2023
- A Single Correspondence Is Enough: Robust Global Registration to Avoid Degeneracy in Urban Environments. ICRA'2022
- SC^2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration. CVPR'2022
- A Practical O (N2) Outlier Removal Method for Point Cloud Registration. TPAMI 2021.
- A review on robust M-estimators for regression analysis. 2021
- Graduated Non-Convexity for Robust Spatial Perception: From Non-Minimal Solvers to Global Outlier Rejection. ICRA 2020.
- TEASER: Fast and Certifiable Point Cloud Registration. T-RO'2020
- A Practical Maximum Clique Algorithm for Matching with Pairwise Constraints. 2019
- GORE: Guaranteed Outlier Removal for Point Cloud Registration with Correspondences. TPAMI'2018
- FGR: Fast Global Registration. ECCV'2016
- On the Unification of Line Processes, Outlier Rejection, and Robust Statistics with Applications in Early Vision. IJCV 1996
- [Deeplearning] A Comprehensive Survey and Taxonomy on Point Cloud Registration Based on Deep Learning. ARXIV 2024
- [Nonrigid] A survey of non-rigid 3D registration. arxiv. 2022
- [Descriptor design] Evaluating Local Geometric Feature Representations for 3D Rigid Data Matching. 2019 TIP
- [Descriptor application scenario] A Comprehensive Performance Evaluation of 3D Local Feature Descriptors. 2016 IJCV.
- [Descriptor for indoor,outdoor] Evaluation of 3D feature descriptors for multi-modal data registration. 2013 IC3DV
- [Descriptor with color]Influence of Colour and Feature Geometry on Multi-modal 3D Point Clouds Data Registration. 2014 IC3DV
- [Descriptor for large-scale scene]An Evaluation of Local Shape Descriptors in Probabilistic Volumetric Scenes. BMVC 2012
- [Detector] Performance Evaluation of 3D Keypoint Detectors. 2012 IJCV
- [Robust Estimation] A Performance Evaluation of Correspondence Grouping Methods for 3D Rigid Data Matching. TPAMI'2019
- [RANSAC-type] A Comparative Analysis of RANSAC Techniques Leading to Adaptive Real-Time Random Sample Consensus. ECCV 2008.
- [ICP on slam] Comparing ICP variants on real-world data sets. 2013 Autonoumous Robots.
- [Rigid Non-rigid] Registration of 3D point clouds and meshes: A survey from rigid to nonrigid. 2012 TVCG
- [LiDAR] Registration of Laser Scanning Point Clouds: A Review. 2018 Sensors.
- [Defomable Correspondence]Recent advances in shape correspondence. 2019 Visual Computer
- [Correspondence] A Survey on Shape Correspondence. CGF 2012
- [Corase and Fine Registration]A review of recent range image registration methodswith accuracy evaluation. IVC 2006.
- Recent developments and trends in point set registration methods。 2017
- [SE2 SE3 Lie group]
- [SE3 Lie group]
- [Recover euler angle from matrix]
- [CMU ICP-variant lecture]
- [Stanford Quaternion]
- [EM and GMM]
- [EM and GMM]
- [SIFT]
- [ADMM]
- [Wiki Point set registration]
- [Point-to-Point, SVD]
- [Point-to-Plane, lineear approximation]
- [Point-to-Plane, Rodrigues approximation]
- [Mutual Information]
- Phase-Congruency-Based Scene Abstraction Approach for 2D-3D Registration of Aerial Optical and LiDAR Images. AEORS 2020
- DRMIME: Differentiable Mutual Information and Matrix Exponential for Multi-Resolution Image Registration. 2020
- Multimodal Remote Sensing Image Registration Methods and Advancements: A Survey. RS 2021
- Co-Attention for Conditioned Image Matching
- Automatic UAV image geo-registration by matching UAV images to georeferenced image data. Remote Sensing 2017
- Universal correspondence network. arXiv 2016.
- Mutual-Information-Based Registration of Medical Images: A Survey. 2003
- (Optimization)Comparative evaluation of multiresolution optimization strategies for multimodality image registration by maximization of mutual information. 1999
- (classic) Alignment by Maximization of Mutual Information. 1997
- [3DCSR, 2021, cross-source: Kinect_Lidar and Kinect_SFM ]
- [nuScenes, 2020, LiDAR like kitti]
- [WHU-TLS,2020, TLS]
- [RESSO,2019, TLS]
- [ETH PRS TLS]
- [ETH ASL]
Ningli Xu, website
We also did a critical review and performance evaluation of SOTA point cloud registration algorithms (including SpinNet, TEASER++, PointDSC, Generalized ICP, Symmetric ICP, Fast and Robust ICP and more). They are evalated on three challenging datasets (RESSO, Whu-TLS, OSUCampus) with hugh difference in overlap, scene context and resolution. Our analysis allows for exploring the strengths, applicility challenges and future trends of these methods. Please reach out to this document for more details!
@article{xu2023point,
title={Point cloud registration for LiDAR and photogrammetric data: A critical synthesis and performance analysis on classic and deep learning algorithms},
author={Xu, Ningli and Qin, Rongjun and Song, Shuang},
journal={ISPRS Open Journal of Photogrammetry and Remote Sensing},
pages={100032},
year={2023},
publisher={Elsevier}
}
'''