Event-based Shape from Polarization with Spiking Neural Networks

TL;DR

This paper introduces Spiking Neural Networks for event-based shape from polarization, achieving comparable accuracy to traditional methods while significantly improving energy efficiency and computational performance.

Contribution

It presents novel Single-Timestep and Multi-Timestep Spiking UNets for surface normal estimation from polarization data, advancing SNN applications in event-based sensing.

Findings

Models match state-of-the-art accuracy in surface normal estimation.

Spiking Neural Networks offer superior energy efficiency over traditional ANNs.

Effective processing of event-based shape data with reduced computational demands.

Abstract

Recent advances in event-based shape determination from polarization offer a transformative approach that tackles the trade-off between speed and accuracy in capturing surface geometries. In this paper, we investigate event-based shape from polarization using Spiking Neural Networks (SNNs), introducing the Single-Timestep and Multi-Timestep Spiking UNets for effective and efficient surface normal estimation. Specificially, the Single-Timestep model processes event-based shape as a non-temporal task, updating the membrane potential of each spiking neuron only once, thereby reducing computational and energy demands. In contrast, the Multi-Timestep model exploits temporal dynamics for enhanced data extraction. Extensive evaluations on synthetic and real-world datasets demonstrate that our models match the performance of state-of-the-art Artifical Neural Networks (ANNs) in estimating surface normals, with the added advantage of superior energy efficiency. Our work not only contributes to the advancement of SNNs in event-based sensing but also sets the stage for future explorations in optimizing SNN architectures, integrating multi-modal data, and scaling for applications on neuromorphic hardware.