Published on Wed Nov 06 2019

SRINet: Learning Strictly Rotation-Invariant Representations for Point Cloud Classification and Segmentation

Xiao Sun, Zhouhui Lian, Jianguo Xiao

Point cloud analysis has drawn broader attentions due to its increasing demands. Despite the impressive performance has been achieved, researchers neglect the fact that the orientation of point cloud data is aligned. The proposed method can extract strictly rotation-invariantrepresentations for point cloud recognition.

0
0
0
Abstract

Point cloud analysis has drawn broader attentions due to its increasing demands in various fields. Despite the impressive performance has been achieved on several databases, researchers neglect the fact that the orientation of those point cloud data is aligned. Varying the orientation of point cloud may lead to the degradation of performance, restricting the capacity of generalizing to real applications where the prior of orientation is often unknown. In this paper, we propose the point projection feature, which is invariant to the rotation of the input point cloud. A novel architecture is designed to mine features of different levels. We adopt a PointNet-based backbone to extract global feature for point cloud, and the graph aggregation operation to perceive local shape structure. Besides, we introduce an efficient key point descriptor to assign each point with different response and help recognize the overall geometry. Mathematical analyses and experimental results demonstrate that the proposed method can extract strictly rotation-invariant representations for point cloud recognition and segmentation without data augmentation, and outperforms other state-of-the-art methods.

Mon Jul 02 2018
Computer Vision
PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentation
PointSIFT encodes information of different orientations and is adaptive to scale of shape. PointSIFT module can be integrated into various PointNet-based architecture to improve representation ability.
0
0
0
Tue Sep 15 2020
Computer Vision
A Self Contour-based Rotation and Translation-Invariant Transformation for Point Clouds Recognition
Self Contour-based Transformation (SCT) can be flexibly integrated into existing point cloud recognition models against arbitrary rotations. The SCT provides efficient andhematically proved rotation and translation invariance by introducing rotation and Translation-Invariant Transformation.
0
0
0
Tue Oct 29 2019
Computer Vision
POIRot: A rotation invariant omni-directional pointnet
Point-cloud is an efficient way to represent 3D world. Analysis of point-cloud deals with understanding the underlying 3D geometric structure. But due to the lack of smooth topology, standard correlation can not be directly applied on point- cloud.
0
0
0
Sun Jul 19 2020
Machine Learning
Mapping in a cycle: Sinkhorn regularized unsupervised learning for point cloud shapes
We propose an unsupervised learning framework with the pretext task of finding dense correspondences between point cloud shapes from the same category. We incorporate in the formulation a regularization term based on Sinkhorn normalization to enhance the learned pointwise mappings.
0
0
0
Wed Mar 03 2021
Computer Vision
EllipsoidNet: Ellipsoid Representation for Point Cloud Classification and Segmentation
Point cloud patterns are hard to learn because of the implicit local geometry features among the orderless points. In this paper, we propose a novel 2D representation method that projects a point cloud onto an ellipsoid surface space, where local geometry is well exposed.
0
0
0
Mon Aug 09 2021
Computer Vision
DRINet: A Dual-Representation Iterative Learning Network for Point Cloud Segmentation
We present a novel architecture for point cloud segmentation with dual-representation iterative learning. DRINet mainly consists of two modules called Sparse Point-Voxel Feature Extraction and Sparse Voxel-Point Feature Extraction.
1
0
0