3D-GFE: A Three-Dimensional Geometric-Feature Extractor for Point Cloud Data
Journal
2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2021 - Proceedings
Pages
2013-2017
Date Issued
2021
Author(s)
Abstract
In this paper, we propose a novel framework that extracts rotation-invariant features relative to the centroid and the reference point in a local point set. Furthermore, we search different scales of nearest neighbors simultaneously to acquire more rotation-invariant information around certain specific point cloud data. We evaluate our architecture with two point cloud tasks, object classification and part segmentation. Experiment results show that our method generates consistent results on randomly rotated data and achieves state-of-the-art performance without any rotational data augmentation. For classification, when training and testing with arbitrary rotations, our model is able to reach averagely 89.0% and 73.5% accuracy on the ModelNet40 and ScanObjectNN datasets, respectively. On the ShapeNet dataset, which is a part segmentation task, our model can achieve 77.7% mIOU. © 2021 APSIPA.
Subjects
Classification; Geometric-Feature Descriptor; Point Cloud; Rotation-Invariant; Segmentation
Other Subjects
Nearest neighbor search; Rotation; Feature descriptors; Feature extractor; Geometric feature; Geometric-feature descriptor; Point cloud data; Point-clouds; Reference points; Rotation invariant; Rotation invariant features; Segmentation; Classification (of information)
Type
conference paper