Robust global registration (original) (raw)
Related papers
3D Point Set Registration based on Hierarchical Descriptors
Journal of WSCG
Registering partial point clouds is crucial in numerous applications in the field of robotics, vision, and graphics. For arbitrary configurations, the registration problem requires an initial global alignment, which is computationally expensive and often still requires refinement. In this paper, we propose 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. Registration is performed by matching descriptors of increasing resolution – which the continuous surfaces allow us to choose arbitrarily high – while restricting the search space according to the hierarchy. We evaluated our method on a large set of pair-wise registration problems, demonstrating very competitive registration accuracy that often makes subsequent refinement with a local method unnecessary.
2021
Registering partial shapes plays an important role in numerous applications in the fields of robotics, vision, and graphics. An essential problem of registration algorithms is the determination of correspondences between surfaces. In this paper, we provide a 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. Instead of using a discrete point set for correspondence search, the approach is based on a locally reconstructed continuous moving least squares surface to overcome sampling mismatches in the input shapes. Furthermore, MLS-based correspondences are highly robust to noise. We demonstrate that this strategy outperforms existing approaches in terms of registration accuracy by combining it with the SparseICP local registration algorithm. Our extensive evaluation over several thousand scans from different sources verify that MLS-based approach results in a significant increase in alignment accuracy, surpassing state-of-theart feature-based and probabilistic methods. At the same time, it allows an efficient implementation that introduces only a modest computational overhead.
Registration of 3D Point Clouds and Meshes: A Survey from Rigid to Nonrigid
IEEE Transactions on Visualization and Computer Graphics, 2000
3D surface registration transforms multiple 3D datasets into the same coordinate system so as to align overlapping components of these sets. Recent surveys have covered different aspects of either rigid or non-rigid registration, but seldom discuss them as a whole. Our study serves two purposes: (i) to give a comprehensive survey of both types of registration, focusing on 3D point clouds and meshes, and (ii) to provide a better understanding of registration from the perspective of data fitting. Registration is closely related to data fitting in that it comprises three core interwoven components: model selection, correspondences & constraints and optimization. Study of these components (i) provides a basis for comparison of the novelties of different techniques, (ii) reveals the similarity of rigid and non-rigid registration in terms of problem representations, and (iii) shows how over-fitting arises in non-rigid registration and the reasons for increasing interest in intrinsic techniques. We further summarise some practical issues of registration which include initializations and evaluations, and discuss some of our own observations, insights and foreseeable research trends.
Registration of 3D - Patterns and Shapes with Characteristic Points
Proceedings of the First International Conference on Computer Vision Theory and Applications, 2006
We study approximation algorithms for a matching problem that is motivated by medical applications. Given a small set of points P ⊂ R 3 and a surface S, the optimal matching of P with S is represented by a rigid transformation which maps P as 'close as possible' to S. Previous solutions either require polynomial runtime of high degree or they make use of heuristic techniques which could be trapped in some local minimum. We propose a modification of the problem setting by introducing small subsets of so called characteristic points P c ⊆ P and Sc ⊆ S, and assuming that points from Pc must be matched with points from Sc. We focus our attention on the first nontrivial case that occurs if |P c| = 2, and show that this restriction results in new fast and reliable algorithms for the matching problem. In contrast to heuristic approaches our algorithm provides guarantees on the approximation factor of the matching. Experimental results are provided for surfaces reconstructed from real and synthetic data.
Robust Shape Registration using Fuzzy Correspondences
arXiv (Cornell University), 2017
Shape registration is the process of aligning one 3D model to another. Most previous methods to align shapes with no known correspondences attempt to solve for both the transformation and correspondences iteratively. We present a shape registration approach that solves for the transformation using fuzzy correspondences to maximize the overlap between the given shape and the target shape. A coarse to fine approach with Levenberg-Marquardt method is used for optimization. Real and synthetic experiments show our approach is robust and outperforms other state of the art methods when point clouds are noisy, sparse, and have non-uniform density. Experiments show our method is more robust to initialization and can handle larger scale changes and rotation than other methods. We also show that the approach can be used for 2D-3D alignment via raypoint alignment. 1.1. Related Works 3D registration is well studied problem with many different approaches, we direct the reader to [5] for a more 1
PLOS ONE, 2015
We present a probabilistic registration algorithm that robustly solves the problem of rigidbody alignment between two shapes with high accuracy, by aptly modeling measurement noise in each shape, whether isotropic or anisotropic. For point-cloud shapes, the probabilistic framework additionally enables modeling locally-linear surface regions in the vicinity of each point to further improve registration accuracy. The proposed Iterative Most-Likely Point (IMLP) algorithm is formed as a variant of the popular Iterative Closest Point (ICP) algorithm, which iterates between point-correspondence and point-registration steps. IMLP's probabilistic framework is used to incorporate a generalized noise model into both the correspondence and the registration phases of the algorithm, hence its name as a most-likely point method rather than a closest-point method. To efficiently compute the most-likely correspondences, we devise a novel search strategy based on a principal direction (PD)-tree search. We also propose a new approach to solve the generalized total-least-squares (GTLS) sub-problem of the registration phase, wherein the point correspondences are registered under a generalized noise model. Our GTLS approach has improved accuracy, efficiency, and stability compared to prior methods presented for this problem and offers a straightforward implementation using standard least squares. We evaluate the performance of IMLP relative to a large number of prior algorithms including ICP, a robust variant on ICP, Generalized ICP (GICP), and Coherent Point Drift (CPD), as well as drawing close comparison with the prior anisotropic registration methods of GTLS-ICP and A-ICP. The performance of IMLP is shown to be superior with respect to these algorithms over a wide range of noise conditions, outliers, and misalignments using both mesh and point-cloud representations of various shapes.
Vote based correspondence for 3D point-set registration
Given two views of a static scene, estimation of correspondences between them is required for various computer vision tasks, such as 3D reconstruction and registration, motion and structure estimation, and object recognition. Without loss of generality, this paper treats the correspondence-estimation problem in the context of feature-based rangescan registration of widely separated views and presents a novel approach to obtain globally consistent set of correspondences. In this paper, we define the notion of a weak feature, and follow the approach that avoids early commitment to the "best" match. It instead considers multiple candidate matches for each feature, and eventually models and solves correspondence-estimation as an optimization problem viz. weighted bipartite matching. We focus on developing a robust approach that succeeds in the presence of significant noise and sparsity in the input.
Invariant features for automatic coarse registration of point-based surfaces
2006
Automatic coarse alignment, or registration, of partially overlapping three dimensional (3D) shapes is a fundamental problem of the shape acquisition and modelling pipeline. This paper describes a new approach to automatic coarse pair-wise registration of partially overlapping 3D point sets which are commonly generated by laser scanners, structured light systems or stereo. The approach is based on the characterization of
Point-cloud registration using 3D shape contexts
2012
The problem of aligning scans from a range sensor is central to 3D mapping for robots. In previous work we demonstrated a lightweight descriptor-based registration method that is suitable for creating maps from range images produced by devices such as the XBOX Kinect. For computational reasons, simple descriptors were used based only on the distribution of distances between points. In this paper, we present an alternative approach using 3D Shape Contexts that also retains angular information thereby producing descriptors that are more unique. Although this increases the computational load, intrinsic properties of the descriptor facilitate keypoint selection, leading to a more robust registration framework. This also provides greater flexibility when applying the method to sparse point clouds such as those produced by laser range scanners. Results are shown for registering new data acquired from an underground mine environment.
Geometry and Convergence Analysis of Algorithms for Registration of 3D Shapes
International Journal of Computer Vision, 2006
The computation of a rigid body transformation which optimally aligns a set of measurement points with a surface and related registration problems are studied from the viewpoint of geometry and optimization. We provide a convergence analysis for known registration algorithms such as ICP and introduce new algorithms with an improved local and global convergence behavior. Most of our work deals with the fundamental problem of registering two views (scans, surfaces) with unknown correspondences. It is then shown how to extend the concepts to the simultaneous registration of an arbitrary number of views.