Sharpening Your Density Fields: Spiking Neuron Aided Fast Geometry Learning

TL;DR

This paper introduces a dynamic threshold adjustment mechanism using spiking neurons to improve the efficiency and robustness of geometry extraction in Neural Radiance Fields, reducing manual tuning and enhancing output sharpness.

Contribution

It proposes a novel spiking neuron-based method with a round-robin strategy to stabilize training and improve geometry extraction in NeRF without manual threshold tuning.

Findings

Significantly improves geometry sharpness and accuracy in NeRF.

Reduces manual threshold tuning and computational overhead.

Enhances robustness across synthetic and real-world datasets.

Abstract

Neural Radiance Fields (NeRF) have achieved remarkable progress in neural rendering. Extracting geometry from NeRF typically relies on the Marching Cubes algorithm, which uses a hand-crafted threshold to define the level set. However, this threshold-based approach requires laborious and scenario-specific tuning, limiting its practicality for real-world applications. In this work, we seek to enhance the efficiency of this method during the training time. To this end, we introduce a spiking neuron mechanism that dynamically adjusts the threshold, eliminating the need for manual selection. Despite its promise, directly training with the spiking neuron often results in model collapse and noisy outputs. To overcome these challenges, we propose a round-robin strategy that stabilizes the training process and enables the geometry network to achieve a sharper and more precise density distribution with minimal computational overhead. We validate our approach through extensive experiments on both synthetic and real-world datasets. The results show that our method significantly improves the performance of threshold-based techniques, offering a more robust and efficient solution for NeRF geometry extraction.