Fast Global Registration

  title={Fast Global Registration},
  author={Qian-Yi Zhou and Jaesik Park and Vladlen Koltun},
  booktitle={European Conference on Computer Vision},
We present an algorithm for fast global registration of partially overlapping 3D surfaces. The algorithm operates on candidate matches that cover the surfaces. A single objective is optimized to align the surfaces and disable false matches. The objective is defined densely over the surfaces and the optimization achieves tight alignment with no initialization. No correspondence updates or closest-point queries are performed in the inner loop. An extension of the algorithm can perform joint… 

TECHNISCHE BERICHTE TECHNICAL REPORTS Moving Least Squares Correspondences for Iterative Point Set Registration

An in-depth evaluation of an approach that computes high-quality correspondences for pair-wise closest point-based iterative registration and compare the results with state-of-the-art registration algorithms and demonstrates that this strategy out-performs existing approaches in terms of registration accuracy by combining it with the SparseICP local registration algorithm.

Efficient and Robust Registration on the 3D Special Euclidean Group

This work presents a robust, fast and accurate method for registration of 3D scans that optimizes a robust cost function on the intrinsic representation of rigid motions, i.e., the Special Euclidean group SE(3).

3D Point Set Registration based on Hierarchical Descriptors

A pair-wise global registration method that combines the fast convergence made possible by global hierarchical surface descriptors with the arbitrarily fine sampling enabled by continuous surface representations is proposed.

Efficient Global Registration for Nominal/Actual Comparisons

This work proposes a new method for global registration that achieves high success rates and fast registration, even for challenging input data, and demonstrates that the proposed algorithm significantly outperforms the current state of the art, with regards to registration time and success rate.

3D Registration of Curves and Surfaces Using Local Differential Information

Comparative experiments demonstrate that the proposed algorithm is the first effective solution for curve vs surface registration, with the method achieving accurate alignment in situations of small overlap and large percentage of outliers in a fraction of a second.

A Maximum Feasible Subsystem for Globally Optimal 3D Point Cloud Registration

Experimental results demonstrated that the presented algorithm was more accurate and reliable than state-of-the-art registration methods and showed robustness against severe outliers/mismatches.

Fast Multiview 3D Scan Registration Using Planar Structures

This work presents a fast and lightweight method for 3D registration of scenes by exploiting the presence of planar regions that yields results comparable in accuracy with the state-of-the-art while only taking a fraction of computation time compared with conventional approaches that are based on motion estimates through 3D point correspondences.

High-Precision 3D Coarse Registration Using RANSAC and Randomly-Picked Rejections

This paper provides a 3D coarse registration method to solve the local-minimum problem in the ICP algorithm and proposes a Randomly-picked rejection method for this problem.

Globally Optimal Point Set Registration by Joint Symmetry Plane Fitting

  • Lan HuL. Kneip
  • Computer Science
    Journal of Mathematical Imaging and Vision
  • 2021
A globally optimal solver is presented by employing the branch-and-bound paradigm and it is demonstrated that joint symmetry plane fitting leads to a great improvement over the current state of the art in globally optimal point set registration for common objects.

An Improved ICP Algorithm for 3D Point Cloud Registration

The Super 4PCS algorithm is used to implement the initial alignment of point clouds to reduce the probability of ICP algorithm falling into a local optimal solution and a local refinement registration method is proposed by adaptively eliminating the boundary points of the overlap region of two point clouds.



Robust global registration

This work presents an algorithm for the automatic alignment of two 3D shapes ( data and model), without any assumptions about their initial positions, and develops a fast branch-and-bound algorithm based on distance matrix comparisons to select the optimal correspondence set and bring the two shapes into a coarse alignment.

Fully automatic registration of multiple 3D data sets

Efficient variants of the ICP algorithm

  • S. RusinkiewiczM. Levoy
  • Computer Science
    Proceedings Third International Conference on 3-D Digital Imaging and Modeling
  • 2001
An implementation is demonstrated that is able to align two range images in a few tens of milliseconds, assuming a good initial guess, and has potential application to real-time 3D model acquisition and model-based tracking.

Fully Automatic Registration of 3D Point Clouds

We propose a novel technique for the registration of 3D point clouds which makes very few assumptions: we avoid any manual rough alignment or the use of landmarks, displacement can be arbitrarily

Optimal correspondences from pairwise constraints

This paper illustrates how pairwise constraints in combination with graph methods can be used to efficiently find optimal correspondences in computer vision and yields competitive running times compared to state of the art.

Super 4PCS Fast Global Pointcloud Registration via Smart Indexing

This work presents Super 4PCS for global pointcloud registration that is optimal, i.e., runs in linear time and is also output sensitive in the complexity of the alignment problem based on the (unknown) overlap across scan pairs.

4-points congruent sets for robust pairwise surface registration

4PCS, a fast and robust alignment scheme for 3D point sets that uses wide bases, which are known to be resilient to noise and outliers, is introduced and an extension to handle similarity and affine transforms is proposed.

Robust Registration of 2D and 3D Point Sets

A new method of registering point sets is introduced that is comparable in speed to the special-purpose Iterated Closest Point algorithm, and the registration error is directly minimized using general-purpose non-linear optimization (the Levenberg–Marquardt algorithm).

The 3D-3D Registration Problem Revisited

A new framework for globally solving the 3D-3D registration problem with unknown point correspondences is described, grounded on the Lipschitz global optimization theory, which achieves a guaranteed global optimality without any initialization.