ORIGINAL RESEARCH article
Front. Neurosci.
Sec. Neuromorphic Engineering
Volume 19 - 2025 | doi: 10.3389/fnins.2025.1593580
This article is part of the Research TopicSpiking Neural Networks: Enhancing Learning Through Neuro-Inspired AdaptationsView all 6 articles
SpiNeRF: Direct-trained Spiking Neural Networks for Efficient Neural Radiance Field Rendering
Provisionally accepted
- 1Institute of Automation, Chinese Academy of Sciences (CAS), Beijing, China
- 2School of Future Technology, University of Chinese Academy of Sciences, Beijing, Beijing, China
- 3China Electric Power Research Institute (CEPRI), Beijing, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Spiking neural networks (SNNs) have recently demonstrated significant progress across various computational tasks, due to their potential for energy efficiency. Neural Radiance Fields (NeRFs), excel at rendering high-quality 3D scenes but require substantial energy consumption, with limited exploration of energy-saving solutions from a neuromorphic approach. In this paper, we present SpiNeRF, a novel method that integrates the sequential processing capabilities on SNNs with the ray-casting mechanism of NeRFs, aiming to enhance compatibility and unlock new prospective for energy efficient 3D scene synthesis. Unlike conventional SNN encoding schemes, our method considers the spatial continuity inherent in NeRF, achieving superior rendering quality. To further improve training and inference efficiency, we adopt a hybrid volumetric representation that allows the predefinition and masking of invalid sampled points along pixel-rendering rays. However, this masking introduces irregular temporal length, making it intractable for hardware processors, such as graphics processing units (GPUs) to conduct effective parallel training. To address this issue, we present two methods: Temporal padding (TP) and temporal condensingand-padding (TCP). Experiments on multiple datasets demonstrate that our method outperforms previous SNN encoding schemes and artificial neural network (ANN) quantization methods in both rendering quality and energy efficiency. Compared to the full-precision ANN baseline, our method reduces energy consumption by up to 72.95% while maintaining comparable synthesis quality. Further verification using a neuromorphic hardware simulator shows that TCP-based SpiNeRF achieves additional energy efficiency gains over the ANN-based approaches by leveraging the advantages of neuromorphic computing. Codes are in https://github.com/Ikarosy/ SpikingNeRF-of-CASIA.
Keywords: spiking neural networks, neuromorphic computing, 3D rendering, Neural Radiance Fields, Efficient rendering, efficient SNN data encoding
Received: 14 Mar 2025; Accepted: 25 Jun 2025.
Copyright: © 2025 Yao, Hu, Zhou, Liu, Mo, Zhu, Zhuge and Cheng. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Jian Cheng, Institute of Automation, Chinese Academy of Sciences (CAS), Beijing, China
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.