Spiking-NeRF: Spiking Neural Network for Energy-Efficient Neural Rendering

Author:

Li Ziwen1ORCID,Ma Yu1ORCID,Zhou Jindong1ORCID,Zhou Pingqiang1ORCID

Affiliation:

1. School of Information Science and Technology, ShanghaiTech University, Shanghai, China

Abstract

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.

Funder

National Natural Science Foundation of China

Publisher

Association for Computing Machinery (ACM)

Reference54 articles.

1. TrueNorth: Design and Tool Flow of a 65 mW 1 Million Neuron Programmable Neurosynaptic Chip

2. Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields

3. NeRD: Neural Reflectance Decomposition from Image Collections

4. Tong Bu Jianhao Ding Zhaofei Yu and Tiejun Huang. 2022. Optimized Potential Initialization for Low-Latency Spiking Neural Networks. arXiv: 2202.01440. Retrieved from https://arxiv.org/abs/2202.01440

5. Spiking Deep Convolutional Neural Networks for Energy-Efficient Object Recognition

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3