Noise-Injected Spiking Graph Convolution for Energy-Efficient 3D Point Cloud Denoising

TL;DR

This paper introduces noise-injected spiking graph convolutional networks for energy-efficient 3D point cloud denoising, demonstrating competitive accuracy and significant energy savings on benchmark datasets, and exploring hybrid models for improved performance.

Contribution

It proposes novel noise-injected spiking neurons and graph convolutional networks for 3D point cloud denoising, highlighting the potential of SNNs in regression tasks and energy-efficient applications.

Findings

Achieved low accuracy loss compared to ANN-based methods.

Significantly reduced energy consumption on benchmark datasets.

Demonstrated effectiveness of hybrid SNN-ANN architecture.

Abstract

Spiking neural networks (SNNs), inspired by the spiking computation paradigm of the biological neural systems, have exhibited superior energy efficiency in 2D classification tasks over traditional artificial neural networks (ANNs). However, the regression potential of SNNs has not been well explored, especially in 3D point cloud processing. In this paper, we propose noise-injected spiking graph convolutional networks to leverage the full regression potential of SNNs in 3D point cloud denoising. Specifically, we first emulate the noise-injected neuronal dynamics to build noise-injected spiking neurons. On this basis, we design noise-injected spiking graph convolution for promoting disturbance-aware spiking representation learning on 3D points. Starting from the spiking graph convolution, we build two SNN-based denoising networks. One is a purely spiking graph convolutional network, which achieves low accuracy loss compared with some ANN-based alternatives, while resulting in significantly reduced energy consumption on two benchmark datasets, PU-Net and PC-Net. The other is a hybrid architecture that combines ANN-based learning with a high performance-efficiency trade-off in just a few time steps. Our work lights up SNN's potential for 3D point cloud denoising, injecting new perspectives of exploring the deployment on neuromorphic chips while paving the way for developing energy-efficient 3D data acquisition devices.