SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters

Abstract

Deep neural networks have enjoyed remarkable success for various vision tasks, however it remains challenging to apply CNNs to domains lacking a regular underlying structures such as 3D point clouds. Towards this we propose a novel convolutional architecture, termed SpiderCNN, to efficiently extract geometric features from point clouds. SpiderCNN is comprised of units called SpiderConv, which extend convolutional operations from regular grids to irregular point sets that can be embedded in R^n, by parametrizing a family of convolutional filters. We design the filter as a product of a simple step function that captures local geodesic information and a Taylor polynomial that ensures the expressiveness. SpiderCNN inherits the multi-scale hierarchical architecture from classical CNNs, which allows it to extract semantic deep features. Experiments on ModelNet40 demonstrate that SpiderCNN achieves state-of-the-art accuracy 92.4% on standard benchmarks, and shows competitive performance on segmentation task.

arXiv commentEuropean Conference on Computer Vision 2018 (ECCV 2018)

References in corpus (4)

• Geometric deep learning: going beyond Euclidean data
• Graph Embedding Techniques, Applications, and Performance: A Survey
• Generative and Discriminative Voxel Modeling with Convolutional Neural Networks
• Learning shape correspondence with anisotropic convolutional neural networks

Cited by in corpus (11)

• DeepGCNs: Making GCNs Go as Deep as CNNs
• Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Features
• PointCNN: Convolution On $\mathcal{X}$-Transformed Points
• PointConv: Deep Convolutional Networks on 3D Point Clouds
• CRA-PCN: Point Cloud Completion with Intra- and Inter-level Cross-Resolution Transformers
• Mitigating the Hubness Problem for Zero-Shot Learning of 3D Objects
• Discrete Rotation Equivariance for Point Cloud Recognition
• PointAR: Efficient Lighting Estimation for Mobile Augmented Reality
• AdvectiveNet: An Eulerian-Lagrangian Fluidic reservoir for Point Cloud Processing
• Multi Voxel-Point Neurons Convolution (MVPConv) for Fast and Accurate 3D Deep Learning
• Zero-shot Learning of 3D Point Cloud Objects