|国家预印本平台
首页|Event-based Shape from Polarization with Spiking Neural Networks

Event-based Shape from Polarization with Spiking Neural Networks

Event-based Shape from Polarization with Spiking Neural Networks

来源:Arxiv_logoArxiv
英文摘要

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.

Aggelos Katsaggelos、Peng Kang、Henry Chopp、Srutarshi Banerjee、Oliver Cossairt

计算技术、计算机技术电子技术应用自动化技术、自动化技术设备

Aggelos Katsaggelos,Peng Kang,Henry Chopp,Srutarshi Banerjee,Oliver Cossairt.Event-based Shape from Polarization with Spiking Neural Networks[EB/OL].(2023-12-26)[2025-08-02].https://arxiv.org/abs/2312.16071.点此复制

评论