AA-ICP: Iterative Closest Point with Anderson Acceleration

Pavlov, Artem L.; Ovchinnikov, Grigory Wv.; Derbyshev, D. Yu.; Tsetserukou, Dzmitry; Oseledets, Ivan

doi:10.1109/icra.2018.8461063

Cited by 90 publications

(57 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Baseline Algorithms We present extensive performance evaluation by comparing with a few point cloud registration algorithms based on geometry. They are: (i) The ICP family, such as ICP [2], G-ICP [28], and AA-ICP [21]; (ii) NDT-P2D [30]; (iii) GMM family, such as GMM-REG [15] and CPD [19]. The implementations of ICP, G-ICP, AA-ICP, and NDT-P2D are from the Point Cloud Library (PCL) [26].…”

Section: Performancementioning

confidence: 99%

DeepVCP: An End-to-End Deep Neural Network for Point Cloud Registration

Wan

Zhou

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

299

168

View full text Add to dashboard Cite

We present DeepICP -a novel end-to-end learningbased 3D point cloud registration framework that achieves comparable registration accuracy to prior state-of-the-art geometric methods. Different from other keypoint based methods where a RANSAC procedure is usually needed, we implement the use of various deep neural network structures to establish an end-to-end trainable network. Our keypoint detector is trained through this end-to-end structure and enables the system to avoid the inference of dynamic objects, leverages the help of sufficiently salient features on stationary objects, and as a result, achieves high robustness. Rather than searching the corresponding points among existing points, the key contribution is that we innovatively generate them based on learned matching probabilities among a group of candidates, which can boost the registration accuracy. Our loss function incorporates both the local similarity and the global geometric constraints to ensure all above network designs can converge towards the right direction. We comprehensively validate the effectiveness of our approach using both the KITTI dataset and the Apollo-SouthBay dataset. Results demonstrate that our method achieves comparable or better performance than the state-of-the-art geometry-based methods. Detailed ablation and visualization analysis are included to further illustrate the behavior and insights of our network. The low registration error and high robustness of our method makes it attractive for substantial applications relying on the point cloud registration task.

show abstract

Section: Performancementioning

confidence: 99%

DeepVCP: An End-to-End Deep Neural Network for Point Cloud Registration

Wan

Zhou

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

299

168

View full text Add to dashboard Cite

show abstract

“…However, its long computational time and need for an inclusion relationship for two-point clouds [5] seriously affects the performance of the ICP algorithm. Hence, many experts and scholars have proposed many approaches to improve the algorithm [6][7][8]. Because of this limitation of the algorithm, ICP and its variants need good initialization to avoid falling into a local minimum.…”

Section: Related Workmentioning

confidence: 99%

Point Cloud Registration Algorithm Based on the Grey Wolf Optimizer

Feng

Tang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

In view of the long computation time and low registration accuracy of the current point cloud registration algorithm, a point cloud registration algorithm based on the grey wolf optimizer (GWO) is proposed, denoted PCR-GW. The algorithm uses the centralization method to solve the translation matrix and then simplifies the points of the initial point cloud models by using the intrinsic shape signatures (ISS) feature. Next, various parameters of the rotation matrix are obtained via the GWO algorithm by employing the quadratic sum of the distances between corresponding points in the simplified point cloud as the objective function. Finally, the point cloud registration process is completed by using the obtained transformation matrix. By conducting a registration experiment on the point cloud library model and comparing PCR-GW with the traditional algorithms, the algorithm proposed in this paper is shown to be promising for improving the computation speed and registration accuracy. INDEX TERMS point cloud registration; feature point extraction; grey wolf optimization algorithm

show abstract

“…The most popular method in local registration is Iterative Closest Point (Besl, McKay, 1992, Chen, Medioni, 1992) and a lot of variants exist (Chen, Medioni, 1992, Rusinkiewicz, Levoy, 2001, Pavlov et al, 2017, Chetverikov et al, 2002. For example, (Babin et al, 2019) compares different cost functions, in order to make ICP robust to outliers.…”

Section: Local Registrationmentioning

confidence: 99%

Automatic Clustering of Celtic Coins Based on 3d Point Cloud Pattern Analysis

Horache

Goulette

Deschaud

et al. 2020

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. The recognition and clustering of coins which have been struck by the same die is of interest for archeological studies. Nowadays, this work can only be performed by experts and is very tedious. In this paper, we propose a method to automatically cluster dies, based on 3D scans of coins. It is based on three steps: registration, comparison and graph-based clustering. Experimental results on 90 coins coming from a Celtic treasury from the II-Ith century BC show a clustering quality equivalent to expert’s work.

show abstract

AA-ICP: Iterative Closest Point with Anderson Acceleration

Cited by 90 publications

References 17 publications

DeepVCP: An End-to-End Deep Neural Network for Point Cloud Registration

DeepVCP: An End-to-End Deep Neural Network for Point Cloud Registration

Point Cloud Registration Algorithm Based on the Grey Wolf Optimizer

Automatic Clustering of Celtic Coins Based on 3d Point Cloud Pattern Analysis

Contact Info

Product

Resources

About