Spiking GS: Towards High-Accuracy and Low-Cost Surface Reconstruction via Spiking Neuron-based Gaussian Splatting

TL;DR

This paper introduces Spiking GS, a novel method that incorporates spiking neurons into Gaussian Splatting to improve 3D surface reconstruction accuracy while reducing computational and storage costs.

Contribution

It proposes integrating spiking neurons into Gaussian Splatting to address bias and inefficiency issues, leading to more accurate and cost-effective 3D reconstructions.

Findings

Achieves higher reconstruction accuracy with lower cost.

Effectively reduces low-opacity parts in Gaussian representations.

Demonstrates improved surface detail preservation.

Abstract

3D Gaussian Splatting is capable of reconstructing 3D scenes in minutes. Despite recent advances in improving surface reconstruction accuracy, the reconstructed results still exhibit bias and suffer from inefficiency in storage and training. This paper provides a different observation on the cause of the inefficiency and the reconstruction bias, which is attributed to the integration of the low-opacity parts (LOPs) of the generated Gaussians. We show that LOPs consist of Gaussians with overall low-opacity (LOGs) and the low-opacity tails (LOTs) of Gaussians. We propose Spiking GS to reduce such two types of LOPs by integrating spiking neurons into the Gaussian Splatting pipeline. Specifically, we introduce global and local full-precision integrate-and-fire spiking neurons to the opacity and representation function of flattened 3D Gaussians, respectively. Furthermore, we enhance the density control strategy with spiking neurons' thresholds and a new criterion on the scale of Gaussians. Our method can represent more accurate reconstructed surfaces at a lower cost. The supplementary material and code are available at https://github.com/zju-bmi-lab/SpikingGS.