Relation-Shape Convolutional Neural Network for Point Cloud Analysis
arXiv:1904.07601
Abstract
Point cloud analysis is very challenging, as the shape implied in irregular points is difficult to capture. In this paper, we propose RS-CNN, namely, Relation-Shape Convolutional Neural Network, which extends regular grid CNN to irregular configuration for point cloud analysis. The key to RS-CNN is learning from relation, i.e., the geometric topology constraint among points. Specifically, the convolutional weight for local point set is forced to learn a high-level relation expression from predefined geometric priors, between a sampled point from this point set and the others. In this way, an inductive local representation with explicit reasoning about the spatial layout of points can be obtained, which leads to much shape awareness and robustness. With this convolution as a basic operator, RS-CNN, a hierarchical architecture can be developed to achieve contextual shape-aware learning for point cloud analysis. Extensive experiments on challenging benchmarks across three tasks verify RS-CNN achieves the state of the arts.
Accepted to CVPR 2019 as an oral presentation. Project page at https://yochengliu.github.io/Relation-Shape-CNN
References in corpus (7)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- PCPNET: Learning Local Shape Properties from Raw Point Clouds
- PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentation
- Dynamic Graph CNN for Learning on Point Clouds
- RGCNN: Regularized Graph CNN for Point Cloud Segmentation
- Deep Learning with Sets and Point Clouds
- Flex-Convolution (Million-Scale Point-Cloud Learning Beyond Grid-Worlds)
Cited by in corpus (7)
- RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds
- PF-Net: Point Fractal Network for 3D Point Cloud Completion
- Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Review
- PaRot: Patch-Wise Rotation-Invariant Network via Feature Disentanglement and Pose Restoration
- 3DRM:Pair-wise relation module for 3D object detection
- Multi Voxel-Point Neurons Convolution (MVPConv) for Fast and Accurate 3D Deep Learning
- Going Deeper with Lean Point Networks