Spiking-NeRF: Spiking Neural Network for Energy-Efficient Neural Rendering
ACM Journal on Emerging Technologies in Computing Systems · 31.07.2024 · 20 (3) · 1-23
DOI: 10.1145/3675808 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Journal on Emerging Technologies in Computing Systems, online erschienen am 26.08.2024. Verfasst von Ziwen Li und 3 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 54 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Artificial Neural Networks (ANNs) have achieved remarkable performance in many artificial intelligence tasks. As the application scenarios become more sophisticated, the computation and energy consumption of ANNs are also constantly increasing, which poses a challenge for deploying ANNs on energy-constrained devices. Spiking Neural Networks (SNNs) provide a promising solution to build energy-efficiency neural networks. However, the current training methods of SNNs cannot output values as precise as ANNs. This limits the applications of SNNs to relatively simple image classification tasks. In this article, we extend the application of SNNs to neural rendering tasks and propose an energy-efficient spiking neural rendering model, called Spiking-NeRF (Spiking Neural Radiance Fields). We first analyze the ANN-to-SNN conversion theory and propose an output scheme for SNNs to obtain the precise scene property values. Then we customize the parameter normalization method for the special network architecture of neural rendering. Furthermore, we present an early termination strategy (ETS) based on the discrete nature of spikes to reduce energy consumption. We evaluate the performance of Spiking-NeRF on both realistic and synthetic scenes. Experimental results show that Spiking-NeRF can achieve comparable rendering performance to ANN-based NeRF with up to \(2.27\times\) energy reduction.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Li, Z., Ma, Y., Zhou, J., & Zhou, P. (2024). Spiking-NeRF: Spiking Neural Network for Energy-Efficient Neural Rendering. ACM Journal on Emerging Technologies in Computing Systems, 20(3), 1-23. https://doi.org/10.1145/3675808
Vancouver
Li Z, Ma Y, Zhou J, Zhou P. Spiking-NeRF: Spiking Neural Network for Energy-Efficient Neural Rendering. ACM Journal on Emerging Technologies in Computing Systems. 2024;20(3):1-23. doi:10.1145/3675808
BibTeX
@article{Li2024,
author = {Li, Ziwen and Ma, Yu and Zhou, Jindong and Zhou, Pingqiang},
title = {Spiking-NeRF: Spiking Neural Network for Energy-Efficient Neural Rendering},
journal = {ACM Journal on Emerging Technologies in Computing Systems},
year = {2024},
volume = {20},
number = {3},
pages = {1--23},
doi = {10.1145/3675808}
}
EUVIMED