CorsNet: 3D Point Cloud Registration by Deep Neural Network

Kurobe, Akiyoshi; Sekikawa, Yusuke; Ishikawa, Kohta; Saitō, Hideo

doi:10.1109/lra.2020.2970946

Cited by 62 publications

(32 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, it integrates more helpful information than traditional methods. Experiments showed that CorsNet is more accurate than the classic ICP method and more accurate than the recently proposed learning-based PointNetLK (PointNet framework based on Lucas and Kanade) and DirectNet (domain-transformation enabled end-to-end deep convolutional neural network), including visible and invisible categories [92].…”

Section: Registration Methods Based On Deep Learningmentioning

confidence: 94%

High-Precision 3D Reconstruction for Small-to-Medium-Sized Objects Utilizing Line-Structured Light Scanning: A Review

2021

View full text Add to dashboard Cite

Three-dimensional reconstruction technology has demonstrated broad application potential in the industrial, construction, medical, forestry, agricultural, and pastural sectors in the last few years. High-quality digital point cloud information exists to help researchers to understand objects and environments. However, current research mainly focuses on making adaptive adjustments to various scenarios and related issues in the application of this technology rather than looking for further improvements and enhancements based on technical principles. Meanwhile, a review of approaches, algorithms, and techniques for high-precision 3D reconstruction utilizing line-structured light scanning, which is analyzed from a deeper perspective of elementary details, is lacking. This paper takes the technological path as the logical sequence to provide a detailed summary of the latest development status of each key technology, which will serve potential users and new researchers in this field. The focus is placed on exploring studies reconstructing small-to-medium-sized objects, as opposed to performing large-scale reconstructions in the field.

show abstract

Section: Registration Methods Based On Deep Learningmentioning

confidence: 94%

High-Precision 3D Reconstruction for Small-to-Medium-Sized Objects Utilizing Line-Structured Light Scanning: A Review

2021

View full text Add to dashboard Cite

show abstract

“…Recent studies have shown that point cloud registration algorithms based on deep learning have higher registration accuracy than classic point cloud registration algorithms [26][27][28][29][30].…”

Section: Deep Learning-based Registration Algorithmsmentioning

confidence: 99%

MPCR-Net: Multiple Partial Point Clouds Registration Network Using a Global Template

Su¹,

Wang²,

Chen³

et al. 2021

Preprint

View full text Add to dashboard Cite

With the advancement of photoelectric technology and computer image processing technology, the visual measurement method based on point clouds is gradually applied to the 3D measurement of large workpieces. Point cloud registration is a key step in 3D measurement, and its registration accuracy directly affects the accuracy of 3D measurements. In this study, we designed a novel MPCR-Net for multiple partial point cloud registration networks. First, an ideal point cloud was extracted from the CAD model of the workpiece and was used as the global template. Next, a deep neural network was used to search for the corresponding point groups between each partial point cloud and the global template point cloud. Then, the rigid body transformation matrix was learned according to these correspondence point groups to realize the registration of each partial point cloud. Finally, the iterative closest point algorithm was used to optimize the registration results to obtain a final point cloud model of the workpiece. We conducted point cloud registration experiments on untrained models and actual workpieces, and by comparing them with existing point cloud registration methods, we verified that the MPCR-Net could improve the accuracy and robustness of the 3D point cloud registration.

show abstract

“…31 Kurobe et al proposed a point cloud registration system based on deep learning, and the system could integrate more useful information than conventional approaches. 32 By the consideration of new discrete curvature parameters, Rantoson et al proposed a registration technique, and a new variant of ICP algorithm is used to reduce registration error. 33 Bergstrom et al proposed a distance varying grid tree structure for on-line use, and the involved registration problem is solved by ICP algorithm.…”

Section: Introductionmentioning

confidence: 99%

A compensation method for the eccentricity and inclination errors of spiral bevel gear based on improved ICP algorithm

Liu

Chen

Fang

2021

Advances in Mechanical Engineering

View full text Add to dashboard Cite

Due to the manufacturing and assembly errors of the spiral bevel gear, the deviations between the measured tooth surface and its theoretical tooth surface will affect the measurement results of the tooth surface. After analyzing the tooth surface deviation of spiral bevel gear, this paper provided a compensation method to compensate the eccentricity and inclination errors by the registration of the theoretical and measured tooth surface. An improved iterative closest point (ICP) algorithm for the registration of the tooth surface was provided. The distance between the point in measured tooth surface and the nearest point in theoretical tooth surface is used to replace the minimum Euclidean distance, and the damping Gauss-Newton method is used to solve the geometric transformation matrix. Simulation experiments were carried out to verify the proposed compensation method. The compensation effect is over 93% for the concave tooth surface and over 89% for the convex tooth surface of the spiral bevel gear. The results also show that the improved ICP algorithm could compensate the eccentricity and inclination errors of the spiral bevel gear more precisely than the basic ICP algorithm.

show abstract

CorsNet: 3D Point Cloud Registration by Deep Neural Network

Cited by 62 publications

References 22 publications

High-Precision 3D Reconstruction for Small-to-Medium-Sized Objects Utilizing Line-Structured Light Scanning: A Review

High-Precision 3D Reconstruction for Small-to-Medium-Sized Objects Utilizing Line-Structured Light Scanning: A Review

MPCR-Net: Multiple Partial Point Clouds Registration Network Using a Global Template

A compensation method for the eccentricity and inclination errors of spiral bevel gear based on improved ICP algorithm

Contact Info

Product

Resources

About