SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters

TL;DR

SpiderCNN introduces a novel convolutional architecture for 3D point clouds, enabling deep learning on irregular data by parameterizing filters that capture local geometric features effectively.

Contribution

The paper presents SpiderCNN, a new convolutional network architecture with parameterized filters designed specifically for irregular point cloud data, extending CNN principles to non-grid domains.

Findings

Achieves 92.4% accuracy on ModelNet40

Demonstrates competitive segmentation performance

Extends CNNs to irregular point sets effectively

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.