Modeling Local Geometric Structure of 3D Point Clouds using Geo-CNN
arXiv:1811.07782
Abstract
Recent advances in deep convolutional neural networks (CNNs) have motivated researchers to adapt CNNs to directly model points in 3D point clouds. Modeling local structure has been proven to be important for the success of convolutional architectures, and researchers exploited the modeling of local point sets in the feature extraction hierarchy. However, limited attention has been paid to explicitly model the geometric structure amongst points in a local region. To address this problem, we propose Geo-CNN, which applies a generic convolution-like operation dubbed as GeoConv to each point and its local neighborhood. Local geometric relationships among points are captured when extracting edge features between the center and its neighboring points. We first decompose the edge feature extraction process onto three orthogonal bases, and then aggregate the extracted features based on the angles between the edge vector and the bases. This encourages the network to preserve the geometric structure in Euclidean space throughout the feature extraction hierarchy. GeoConv is a generic and efficient operation that can be easily integrated into 3D point cloud analysis pipelines for multiple applications. We evaluate Geo-CNN on ModelNet40 and KITTI and achieve state-of-the-art performance.
References in corpus (19)
- Generative and Discriminative Voxel Modeling with Convolutional Neural Networks
- VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
- Dynamic Graph CNN for Learning on Point Clouds
- Multi-view Convolutional Neural Networks for 3D Shape Recognition
- FPNN: Field Probing Neural Networks for 3D Data
- SO-Net: Self-Organizing Network for Point Cloud Analysis
- SPLATNet: Sparse Lattice Networks for Point Cloud Processing
- PU-Net: Point Cloud Upsampling Network
- Multi-View 3D Object Detection Network for Autonomous Driving
- Local Spectral Graph Convolution for Point Set Feature Learning
- Recurrent Slice Networks for 3D Segmentation of Point Clouds
- Visual Relationship Detection with Internal and External Linguistic Knowledge Distillation
- PPFNet: Global Context Aware Local Features for Robust 3D Point Matching
- Multiresolution Tree Networks for 3D Point Cloud Processing
- FoldingNet: Point Cloud Auto-encoder via Deep Grid Deformation
- Fully-Convolutional Point Networks for Large-Scale Point Clouds
- Dynamic Zoom-in Network for Fast Object Detection in Large Images
- The Role of Context Selection in Object Detection
- C-WSL: Count-guided Weakly Supervised Localization