Geometric Back-projection Network for Point Cloud Classification
arXiv:1911.12885
Abstract
As the basic task of point cloud analysis, classification is fundamental but always challenging. To address some unsolved problems of existing methods, we propose a network that captures geometric features of point clouds for better representations. To achieve this, on the one hand, we enrich the geometric information of points in low-level 3D space explicitly. On the other hand, we apply CNN-based structures in high-level feature spaces to learn local geometric context implicitly. Specifically, we leverage an idea of error-correcting feedback structure to capture the local features of point clouds comprehensively. Furthermore, an attention module based on channel affinity assists the feature map to avoid possible redundancy by emphasizing its distinct channels. The performance on both synthetic and real-world point clouds datasets demonstrate the superiority and applicability of our network. Comparing with other state-of-the-art methods, our approach balances accuracy and efficiency.
arXiv comment14 pages, 8 figures
References in corpus (8)
- SGDR: Stochastic Gradient Descent with Warm Restarts
- RGCNN: Regularized Graph CNN for Point Cloud Segmentation
- Local Spectral Graph Convolution for Point Set Feature Learning
- Deep Learning for 3D Point Clouds: A Survey
- GAPNet: Graph Attention based Point Neural Network for Exploiting Local Feature of Point Cloud
- PointGrow: Autoregressively Learned Point Cloud Generation with Self-Attention
- Point Attention Network for Semantic Segmentation of 3D Point Clouds
- Training a Feedback Loop for Hand Pose Estimation