A crucial reason for the success of existing NeRF-based methods is to build a neural density field for the geometry representation via multiple perceptron layers (MLPs). MLPs are continuous functions, however, real geometry or density field is frequently discontinuous at the interface between the air and the surface. Such a contrary brings the problem of unfaithful geometry representation. To this end, this paper proposes spiking NeRF, which leverages spiking neurons and a hybrid Artificial Neural Network (ANN)-Spiking Neural Network (SNN) framework to build a discontinuous density field for faithful geometry representation. Specifically, we first demonstrate the reason why continuous density fields will bring inaccuracy. Then, we propose to use the spiking neurons to build a discontinuous density field. We conduct a comprehensive analysis for the problem of existing spiking neuron models and then provide the numerical relationship between the parameter of the spiking neuron and the theoretical accuracy of geometry. Based on this, we propose a bounded spiking neuron to build the discontinuous density field. Our method achieves SOTA performance. The source code and the supplementary material are available at https://github.com/liaozhanfeng/Spiking-NeRF.

翻译：现有基于NeRF方法成功的关键原因之一在于利用多层感知机（MLPs）构建用于几何表示的神经密度场。然而，MLPs属于连续函数，而真实几何或密度场在空气与表面的交界面处往往是不连续的。这种矛盾导致了几何表示不忠实的问题。为此，本文提出Spiking NeRF，利用脉冲神经元和混合人工神经网络（ANN）-脉冲神经网络（SNN）框架构建不连续密度场，以实现忠实的几何表示。具体而言，我们首先论证了连续密度场为何会导致不精确性。然后，我们提出使用脉冲神经元构建不连续密度场。针对现有脉冲神经元模型存在的问题进行了全面分析，并给出了脉冲神经元参数与几何理论精度之间的数值关系。基于此，我们提出一种有界脉冲神经元来构建不连续密度场。我们的方法达到了最先进的性能（SOTA）。源代码和补充材料见https://github.com/liaozhanfeng/Spiking-NeRF。