Deep Global Registration

Choy, Christopher; Dong, Wei; Koltun, Vladlen

doi:10.1109/cvpr42600.2020.00259

Cited by 408 publications

(401 citation statements)

References 42 publications

Supporting

Mentioning

359

Contrasting

Order By: Relevance

“…For symmetric ICP, we use the formulation that does not rotate the normals (E symm as defined in the paper). Besides ICP-based methods, we also compare with other methods including CPD [25] and GMM-Reg [26] based on statistical frameworks, Teaser++ [34] which uses truncated least squares optimization, as well as DCP [35] and DGR [36] based on deep learning, using their open-source implementations 3 4 5 6 7 . We implement our methods in C++, using the EIGEN library [63] for linear algebra operations.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Fast and Robust Iterative Closest Point

Zhang¹,

Yao²,

Deng³

2021

IEEE Trans. Pattern Anal. Mach. Intell.

120

View full text Add to dashboard Cite

The Iterative Closest Point (ICP) algorithm and its variants are a fundamental technique for rigid registration between two point sets, with wide applications in different areas from robotics to 3D reconstruction. The main drawbacks for ICP are its slow convergence as well as its sensitivity to outliers, missing data, and partial overlaps. Recent work such as Sparse ICP achieves robustness via sparsity optimization at the cost of computational speed. In this paper, we propose a new method for robust registration with fast convergence. First, we show that the classical point-to-point ICP can be treated as a majorization-minimization (MM) algorithm, and propose an Anderson acceleration approach to speed up its convergence. In addition, we introduce a robust error metric based on the Welsch's function, which is minimized efficiently using the MM algorithm with Anderson acceleration. On challenging datasets with noises and partial overlaps, we achieve similar or better accuracy than Sparse ICP while being at least an order of magnitude faster. Finally, we extend the robust formulation to point-to-plane ICP, and solve the resulting problem using a similar Anderson-accelerated MM strategy. Our robust ICP methods improve the registration accuracy on benchmark datasets while being competitive in computational time.

show abstract

Section: Resultsmentioning

confidence: 99%

“…In [34], a truncated least squares optimization is proposed to make the registration insensitive to outliers. Recently, deep learning has also been applied to registration problems [35], [36].…”

Section: Related Workmentioning

confidence: 99%

Fast and Robust Iterative Closest Point

Zhang¹,

Yao²,

Deng³

2021

IEEE Trans. Pattern Anal. Mach. Intell.

120

View full text Add to dashboard Cite

show abstract

“…We compare our method against point‐to‐point ICP [2], point‐to‐plane ICP [18], deep global registration (DGR) [19] and 3D multiview registration (3DMR) [5]. The former two methods are popular ICP‐based methods and the latter two are state‐of‐the‐art deep learning‐based registration approaches.…”

Section: Methodsmentioning

confidence: 99%

Method for registration of 3D shapes without overlap for known 3D priors

Munteanu

2021

Electronics Letters

View full text Add to dashboard Cite

In 3D registration of point clouds, the goal is to find an optimal transformation that aligns the input shapes, provided that they have some overlap. Existing methods suffer from performance degradation when the overlapping ratio between the neighbouring point clouds is small. So far, there is no existing method that can be adopted for aligning shapes with no overlap. In this letter, to the best of knowledge, the first method for the registration of 3D shapes without overlap, assuming that the shapes correspond to partial views of a known semi-rigid 3D prior is presented. The method is validated and compared to existing methods on FAUST, which is a known dataset used for human body reconstruction. Experimental results show that this approach can effectively align shapes without overlap. Compared to existing state-of-theart methods, this approach avoids iterative optimization and is robust to outliers and inherent inaccuracies induced by an initial rough alignment of the shapes. Introduction: 3D registration is a classical and fundamental problem for countless applications. Since commodity depth cameras become less expensive and more accurate, depth images play an increasingly important role in numerous tasks [1]. In order to obtain comprehensive information from 3D scenery, point clouds captured from multiple views need to be aligned. The well-established method is iterative closest point (ICP) [2] based on which a myriad of flavours have been proposed. In ICP, given a source shape and a target shape, the following steps are performed: (1) for each point in the source shape, identify the closest corresponding point in the target shape; (2) predict the transformation by minimizing the mean square Euclidean distance between these correspondences; (3) transform the source shape using the predicted transformation from step 2; (4) iterate the above steps until the mean square distance reaches a pre-defined threshold. ICP and its variants are the dominating methods for the task of 3D registration. However, ICP-based methods assume that the source and target shapes have been roughly aligned with a sufficient overlap.. Deep learning has shown its excellent ability to solve various problems which are difficult or impossible to address using traditional approaches. Recent research strives to explore 3D registration via deep learning [3], [4], [5], [6]. However, these methods are designed for shapes that partially overlap. In this letter, we present a novel deep learning method for 3D shape registration. Compared to the existing methods, the main advantage of our method is that we successfully handled the non-overlapping shape registration problem. We assume that the shapes correspond to partial views of a known semi-rigid 3D prior. This problem is impossible to be addressed using ICP due to the lack of point correspondences. This is addressed in this letter of which the main contributions can be summarized as follows:

show abstract

“…The red underline markers highlight the best case scenarios. Our method FGA is compuationally fast and robust compared to GA [11], BHRGA [12], FGR [13], DGR [14], DCP-v2 [15], FilterReg [16], PointNetLK [17], Fast Robust ICP [18], point-to-point ICP [6], RANSAC [19], GMMReg [20] and CPD [21].…”

Section: B Structure Of the Articlementioning

confidence: 99%

“…Most of them [15], [17], [61], [62] utilize PointNet [55] as a deep feature extractor and feature matching layers for estimating rigid transformations. In contrast, Deep Global Registration (DGR) [14] -which is a data-driven version of Fast Global Registration (FGR) [13] -uses 3D U-Net type feature extractors and a differentiable weighted Procrustes approach.…”

Section: Deep Learning Approachesmentioning

confidence: 99%

Fast Gravitational Approach for Rigid Point Set Registration With Ordinary Differential Equations

et al. 2021

View full text Add to dashboard Cite

This article introduces a new physics-based method for rigid point set alignment called Fast Gravitational Approach (FGA). In FGA, the source and target point sets are interpreted as rigid particle swarms with masses interacting in a globally multiply-linked manner while moving in a simulated gravitational force field. The optimal alignment is obtained by explicit modeling of forces acting on the particles as well as their velocities and displacements with second-order ordinary differential equations of n-body motion. Additional alignment cues can be integrated into FGA through particle masses. We propose a smooth-particle mass function for point mass initialization, which improves robustness to noise and structural discontinuities. To avoid the quadratic complexity of all-to-all point interactions, we adapt a Barnes-Hut tree for accelerated force computation and achieve quasilinear complexity. We show that the new method class has characteristics not found in previous alignment methods such as efficient handling of partial overlaps, inhomogeneous sampling densities, and coping with large point clouds with reduced runtime compared to the state of the art. Experiments show that our method performs on par with or outperforms all compared competing deep-learning-based and general-purpose techniques (which do not take training data) in resolving transformations for LiDAR data and gains state-of-the-art accuracy and speed when coping with different data.

show abstract

Deep Global Registration

Cited by 408 publications

References 42 publications

Fast and Robust Iterative Closest Point

Fast and Robust Iterative Closest Point

Method for registration of 3D shapes without overlap for known 3D priors

Fast Gravitational Approach for Rigid Point Set Registration With Ordinary Differential Equations

Contact Info

Product

Resources

About