Towards Efficient Graph Convolutional Networks for Point Cloud Handling

TL;DR

This paper proposes mathematical insights and optimizations to improve the computational efficiency of graph convolutional networks for point cloud learning, reducing complexity and memory use without sacrificing accuracy.

Contribution

It introduces a simplified and optimized GCN framework based on theoretical analysis, enabling faster and more memory-efficient point cloud processing.

Findings

Reduced computational complexity in GCNs

Decreased memory consumption

Maintained accuracy with optimized networks

Abstract

In this paper, we aim at improving the computational efficiency of graph convolutional networks (GCNs) for learning on point clouds. The basic graph convolution that is typically composed of a $K$-nearest neighbor (KNN) search and a multilayer perceptron (MLP) is examined. By mathematically analyzing the operations there, two findings to improve the efficiency of GCNs are obtained. (1) The local geometric structure information of 3D representations propagates smoothly across the GCN that relies on KNN search to gather neighborhood features. This motivates the simplification of multiple KNN searches in GCNs. (2) Shuffling the order of graph feature gathering and an MLP leads to equivalent or similar composite operations. Based on those findings, we optimize the computational procedure in GCNs. A series of experiments show that the optimized networks have reduced computational complexity, decreased memory consumption, and accelerated inference speed while maintaining comparable accuracy for learning on point clouds. Code will be available at \url{https://github.com/ofsoundof/EfficientGCN.git}.