# Adaptive Time-step Training for Enhancing Spike-Based Neural Radiance Fields

arXiv: https://arxiv.org/abs/2507.23033 · HTML: https://mlsanity.com/paper/2507.23033/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 45 of its 68 references that are in the map.
- First posted on arXiv 30 Jul 2025.

## Builds on (most cited first, 30 of 45)

- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021)
- [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021)
- [TensoRF: Tensorial Radiance Fields](https://mlsanity.com/paper/2203.09517/) (2022)
- [Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations](https://mlsanity.com/paper/1906.01618/) (2019)
- [NeRF++: Analyzing and Improving Neural Radiance Fields](https://mlsanity.com/paper/2010.07492/) (2020)
- [Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields](https://mlsanity.com/paper/2304.06706/) (2023)
- [Surrogate Gradient Learning in Spiking Neural Networks](https://mlsanity.com/paper/1901.09948/) (2019)
- [Nerfstudio: A Modular Framework for Neural Radiance Field Development](https://mlsanity.com/paper/2302.04264/) (2023)
- [Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks](https://mlsanity.com/paper/1706.02609/) (2017)
- [Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networks](https://mlsanity.com/paper/2007.05785/) (2020)
- [Deep Learning in Spiking Neural Networks](https://mlsanity.com/paper/1804.08150/) (2018)
- [Temporal Efficient Training of Spiking Neural Network via Gradient Re-weighting](https://mlsanity.com/paper/2202.11946/) (2022)
- [SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligence](https://mlsanity.com/paper/2310.16620/) (2023)
- [Variable Bitrate Neural Fields](https://mlsanity.com/paper/2206.07707/) (2022)
- [Accurate and efficient time-domain classification with adaptive spiking recurrent neural networks](https://mlsanity.com/paper/2103.12593/) (2021)
- [GLIF: A Unified Gated Leaky Integrate-and-Fire Neuron for Spiking Neural Networks](https://mlsanity.com/paper/2210.13768/) (2022)
- [SEENN: Towards Temporal Spiking Early-Exit Neural Networks](https://mlsanity.com/paper/2304.01230/) (2023)
- [Parallel Spiking Neurons with High Efficiency and Ability to Learn Long-term Dependencies](https://mlsanity.com/paper/2304.12760/) (2023)
- [Binary Opacity Grids: Capturing Fine Geometric Detail for Mesh-Based View Synthesis](https://mlsanity.com/paper/2402.12377/) (2024)
- [Binary Radiance Fields](https://mlsanity.com/paper/2306.07581/) (2023)
- [SpikingResformer: Bridging ResNet and Vision Transformer in Spiking Neural Networks](https://mlsanity.com/paper/2403.14302/) (2024)
- [Recursive-NeRF: An Efficient and Dynamically Growing NeRF](https://mlsanity.com/paper/2105.09103/) (2021)
- [SHACIRA: Scalable HAsh-grid Compression for Implicit Neural Representations](https://mlsanity.com/paper/2309.15848/) (2023)
- [How Far Can We Compress Instant-NGP-Based NeRF?](https://mlsanity.com/paper/2406.04101/) (2024)
- [Exploring Temporal Information Dynamics in Spiking Neural Networks](https://mlsanity.com/paper/2211.14406/) (2022)
- [High-performance deep spiking neural networks with 0.3 spikes per neuron](https://mlsanity.com/paper/2306.08744/) (2023)
- [TC-LIF: A Two-Compartment Spiking Neuron Model for Long-Term Sequential Modelling](https://mlsanity.com/paper/2308.13250/) (2023)
- [HollowNeRF: Pruning Hashgrid-Based NeRFs with Trainable Collision Mitigation](https://mlsanity.com/paper/2308.10122/) (2023)

## Abstract (arXiv)

Spiking Neural Networks (SNNs) provide an energy-efficient computing paradigm for neural rendering, but existing spike-based Neural Radiance Field (NeRF) models usually use a fixed inference time step for all scenes. This fixed temporal budget is inefficient because NeRF follows a scene-specific training paradigm, and different scenes require different temporal capacities to preserve rendering quality. This paper proposes Pretraining-based Adaptive Time-step Adjustment (PATA), a scene-wise adaptive time-step training framework for spike-based NeRF. PATA parameterizes the target inference time step as a trainable variable and optimizes it through a two-stage training process. A hybrid input mode strengthens early time-step outputs, while full-step soft supervision, smoothed rendering loss, and temporal-budget loss jointly maintain rendering fidelity and reduce temporal computation. The learned target time step is shared by all ray samples within a scene, preserving the parallel rendering structure of NeRF. Experiments on INGP-NeRF and TensoRF backbones across Synthetic-NeRF, Mip-NeRF 360, and LLFF show that PATA consistently reduces inference cost while maintaining competitive rendering quality. PATA reduces the estimated inference energy by up to 57.57% on INGP-NeRF and 68.90% on TensoRF, demonstrating its effectiveness across different neural rendering representations.