Corpus ID: 207869702

Rotation Invariant Point Cloud Classification: Where Local Geometry Meets Global Topology

  title={Rotation Invariant Point Cloud Classification: Where Local Geometry Meets Global Topology},
  author={Chenchen Zhao and Jiaqi Yang and Xin Xiong and Angfan Zhu and Zhiguo Cao and Xin Li},
Point cloud analysis is a fundamental task in 3D computer vision. Most previous works have conducted experiments on synthetic datasets with well-aligned data; while real-world point clouds are often not pre-aligned. How to achieve rotation invariance remains an open problem in point cloud analysis. To meet this challenge, we propose a novel approach toward achieving rotation-invariant (RI) representations by combining local geometry with global topology. In our local-global-representation (LGR… Expand
RotPredictor: Unsupervised Canonical Viewpoint Learning for Point Cloud Classification
This work proposes to rotate the point cloud into a canonical viewpoint for boosting the following downstream target task, e.g., object classification and part segmentation, and is an independent plug and play module, which can be employed by any point-based deep learning framework without extra burden. Expand
Convolution on Rotation-Invariant and Multi-Scale Feature Graph for 3D Point Set Segmentation
This article proposes a novel DNN for 3D point set segmentation called Rotation-invariant and Multi-scale feature Graph convolutional neural network, or RMGnet, which is more flexible than the previous methods as it accepts as input any handcrafted 3D shape features having rotation invariance. Expand
A functional approach to rotation equivariant non-linearities for Tensor Field Networks
Learning pose invariant representation is a fundamental problem in shape analysis. Most existing deep learning algorithms for 3D shape analysis are not robust to rotations and are often trained onExpand
Vector Neurons: A General Framework for SO(3)-Equivariant Networks
Invariance and equivariance to the rotation group have been widely discussed in the 3D deep learning community for pointclouds. Yet most proposed methods either use complex mathematical tools thatExpand
3D Object Classification on Partial Point Clouds: A Practical Perspective
A novel algorithm in an alignment-classification manner is proposed in this paper, which consists of an alignment module predicting object pose for the rigid transformation of visible point clouds to their canonical pose and a typical point classifier such as PointNet++ and DGCNN. Expand
Geometric Attention for Prediction of Differential Properties in 3D Point Clouds
This study presents a geometric attention mechanism that can provide normals and sharp feature lines from raw point clouds in a learnable fashion and establishes the usefulness of the proposed technique with several experiments on the prediction of normal vectors and the extraction of feature lines. Expand


ClusterNet: Deep Hierarchical Cluster Network With Rigorously Rotation-Invariant Representation for Point Cloud Analysis
This paper introduces a novel point cloud representation that can be mathematically proved rigorously rotation-invariant, i.e., identical point clouds in different orientations are unified as a unique and consistent representation. Expand
Rotation Invariant Convolutions for 3D Point Clouds Deep Learning
A novel convolution operator for point clouds that achieves rotation invariance is introduced and is able to generalize and achieve consistent results across different scenarios in which training and testing can contain arbitrary rotations. Expand
Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling
Two new operations to improve PointNet with a more efficient exploitation of local structures are presented, one focuses on local 3D geometric structures and the other exploits local high-dimensional feature structures by recursive feature aggregation on a nearest-neighbor-graph computed from 3D positions. Expand
Local Spectral Graph Convolution for Point Set Feature Learning
This article replaces the standard max pooling step with a recursive clustering and pooling strategy, devised to aggregate information from within clusters of nodes that are close to one another in their spectral coordinates, leading to richer overall feature descriptors. Expand
Dynamic Graph CNN for Learning on Point Clouds
This work proposes a new neural network module suitable for CNN-based high-level tasks on point clouds, including classification and segmentation called EdgeConv, which acts on graphs dynamically computed in each layer of the network. Expand
PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentation
Inspired by the outstanding 2D shape descriptor SIFT, a module called PointSIFT is designed that encodes information of different orientations and is adaptive to scale of shape, which outperforms state-of-the-art method on standard benchmark datasets. Expand
Learning Localized Generative Models for 3D Point Clouds via Graph Convolution
This paper focuses on the generator of a GAN and defines methods for graph convolution when the graph is not known in advance as it is the very output of the generator, such that it learns to exploit a self-similarity prior on the data distribution to sample more effectively. Expand
Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data
This paper introduces ScanObjectNN, a new real-world point cloud object dataset based on scanned indoor scene data, and proposes new point cloud classification neural networks that achieve state-of-the-art performance on classifying objects with cluttered background. Expand
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
This paper designs a novel type of neural network that directly consumes point clouds, which well respects the permutation invariance of points in the input and provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing. Expand
PointCNN: Convolution On X-Transformed Points
This work proposes to learn an Χ-transformation from the input points to simultaneously promote two causes: the first is the weighting of the input features associated with the points, and the second is the permutation of the points into a latent and potentially canonical order. Expand