Spiking neuron networks (SNNs) have been thriving on numerous tasks to leverage their promising energy efficiency and exploit their potentialities as biologically plausible intelligence. Meanwhile, the Neural Radiance Fields (NeRF) render high-quality 3D scenes with massive energy consumption, and few works delve into the energy-saving solution with a bio-inspired approach. In this paper, we propose spiking NeRF (SpikingNeRF), which aligns the radiance ray with the temporal dimension of SNN, to naturally accommodate the SNN to the reconstruction of Radiance Fields. Thus, the computation turns into a spike-based, multiplication-free manner, reducing the energy consumption. In SpikingNeRF, each sampled point on the ray is matched onto a particular time step, and represented in a hybrid manner where the voxel grids are maintained as well. Based on the voxel grids, sampled points are determined whether to be masked for better training and inference. However, this operation also incurs irregular temporal length. We propose the temporal condensing-and-padding (TCP) strategy to tackle the masked samples to maintain regular temporal length, i.e., regular tensors, for hardware-friendly computation. Extensive experiments on a variety of datasets demonstrate that our method reduces the $76.74\%$ energy consumption on average and obtains comparable synthesis quality with the ANN baseline.

翻译：脉冲神经网络（SNN）凭借其显著的能效优势及作为生物可解释智能的潜力，已在众多任务中蓬勃发展。与此同时，神经辐射场（NeRF）虽能渲染高质量三维场景，但能耗巨大，目前鲜有研究探索基于生物启发方法的节能方案。本文提出脉冲神经辐射场（SpikingNeRF），通过将辐射光线与SNN的时间维度对齐，使SNN自然适配于辐射场重建。由此，计算转化为基于脉冲、免乘法的模式，从而降低能耗。在SpikingNeRF中，光线上的每个采样点被匹配至特定时间步，并以混合方式表示（同时保留体素网格）。基于体素网格，可判定采样点是否被掩码以实现更优训练与推理。然而，该操作也导致不规则的时间长度。为此，我们提出时间压缩-填充（TCP）策略以处理掩码采样点，从而维持规则时间长度（即规则张量），便于硬件友好计算。在多个数据集上的大量实验表明，本方法平均降低76.74%的能耗，同时取得与ANN基线相当的合成质量。