Event-based Shape from Polarization with Spiking Neural Networks
Kang, Peng, Banerjee, Srutarshi, Chopp, Henry, Katsaggelos, Aggelos, Cossairt, Oliver
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Dec-26-2023
- Country:
- North America > United States
- Europe
- United Kingdom > England
- Cambridgeshire > Cambridge (0.04)
- Germany > Bavaria
- Upper Bavaria > Munich (0.04)
- United Kingdom > England
- Genre:
- Research Report > Promising Solution (0.34)
- Overview > Innovation (0.34)
- Industry:
- Energy (1.00)
- Health & Medicine > Therapeutic Area
- Neurology (0.46)
- Technology: