Discrete Rotation Equivariance for Point Cloud Recognition

Abstract

Despite the recent active research on processing point clouds with deep networks, few attention has been on the sensitivity of the networks to rotations. In this paper, we propose a deep learning architecture that achieves discrete $\mathbf{SO}(2)$/$\mathbf{SO}(3)$ rotation equivariance for point cloud recognition. Specifically, the rotation of an input point cloud with elements of a rotation group is similar to shuffling the feature vectors generated by our approach. The equivariance is easily reduced to invariance by eliminating the permutation with operations such as maximum or average. Our method can be directly applied to any existing point cloud based networks, resulting in significant improvements in their performance for rotated inputs. We show state-of-the-art results in the classification tasks with various datasets under both $\mathbf{SO}(2)$ and $\mathbf{SO}(3)$ rotations. In addition, we further analyze the necessary conditions of applying our approach to PointNet based networks. Source codes at https://github.com/lijx10/rot-equ-net

The 2019 International Conference on Robotics and Automation (ICRA)

References in corpus (13)

• Group Equivariant Convolutional Networks
• Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
• Generative and Discriminative Voxel Modeling with Convolutional Neural Networks
• VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
• On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groups
• Rotation equivariant vector field networks
• FusionNet: 3D Object Classification Using Multiple Data Representations
• PointCNN: Convolution On $\mathcal{X}$-Transformed Points
• SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters
• N-body Networks: a Covariant Hierarchical Neural Network Architecture for Learning Atomic Potentials
• Intertwiners between Induced Representations (with Applications to the Theory of Equivariant Neural Networks)
• Polar Transformer Networks
• Warped Convolutions: Efficient Invariance to Spatial Transformations

Cited by in corpus (2)

• Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Review
• Equivariant Point Network for 3D Point Cloud Analysis