Spinnet: Learning a general surface descriptor for 3d point cloud registration

S Ao, Q Hu, B Yang, A Markham… - Proceedings of the …, 2021 - openaccess.thecvf.com
Extracting robust and general 3D local features is key to downstream tasks such as point
cloud registration and reconstruction. Existing learning-based local descriptors are either …

Gpa-net: No-reference point cloud quality assessment with multi-task graph convolutional network

Z Shan, Q Yang, R Ye, Y Zhang, Y Xu… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
With the rapid development of 3D vision, point cloud has become an increasingly popular
3D visual media content. Due to the irregular structure, point cloud has posed novel …

Trigonometric projection statistics histograms for 3D local feature representation and shape description

X Liu, A Li, J Sun, Z Lu - Pattern Recognition, 2023 - Elsevier
Feature representation as a significant approach to three-dimensional (3D) shape
description has been widely employed in computer vision. However, most existing methods …

You only train once: Learning general and distinctive 3D local descriptors

S Ao, Y Guo, Q Hu, B Yang… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Extracting distinctive, robust, and general 3D local features is essential to downstream tasks
such as point cloud registration. However, existing methods either rely on noise-sensitive …

FApSH: An effective and robust local feature descriptor for 3D registration and object recognition

B Zhao, Z Wang, X Chen, X Fang, Z Jia - Pattern Recognition, 2024 - Elsevier
Abstract Three-dimensional (3D) local feature descriptor plays an important role in 3D
computer vision because it is widely used to build point-to-point correspondences in many …

Registration of 3D point clouds using a local descriptor based on grid point normal

J Wang, B Wu, J Kang - Applied Optics, 2021 - opg.optica.org
The coarse-to-fine method is the prime technology for point cloud registration in 3D
reconstruction. Aimed at the problem of low accuracy of coarse registration for the partially …

Adaptive milling for contours on deformed surface based on on-machine measurement and optimized parallel projection

B Yi, R Li, W Li, X Wang, S Wu, N Huang - The International Journal of …, 2023 - Springer
Machining contours on a large thin-walled part is a difficult task due to inevitable
deformation of the actual part. The deformation of the contour can significantly influence the …

The Z-axis, X-axis, Weight and Disambiguation Methods for Constructing Local Reference Frame in 3D Registration: An Evaluation

B Zhao, X Fang, J Yue, X Chen, X Le… - arXiv preprint arXiv …, 2022 - arxiv.org
The local reference frame (LRF), as an independent coordinate system generated on a local
3D surface, is widely used in 3D local feature descriptor construction and 3D transformation …

Approach to construct fast and robust local reference frames based on a point cloud

J Huang, S Sun, C Liang, T Huang - Applied Optics, 2024 - opg.optica.org
The construction of local reference frames (LRFs) holds a foundational role with widespread
application spanning the realms of point cloud registration, object recognition, etc. This work …

SliceLRF: A Local Reference Frame Sliced along the Height on the 3D Surface

B Zhong, D Li - Sensors, 2023 - mdpi.com
The local reference frame (LRF) plays a vital role in local 3D shape description and
matching. Numerous LRF methods have been proposed in recent decades. However, few …