用脉冲神经元动态调阈值，让三维重建更准更快
Sharpening Your Density Fields: Spiking Neuron Aided Fast Geometry Learning
- 引入脉冲神经元自动调节等值面阈值
- 训练稳定后几何密度分布更清晰锐利
- 适合需要高效精确三维重建的场景
神经辐射场（NeRF）在神经渲染中取得显著进展。传统几何提取依赖基于手工设定阈值的等值面算法（如Marching Cubes），但该阈值需针对不同场景反复调试，实用性受限。本文提出一种脉冲神经元机制，在训练过程中动态调整阈值，避免人工干预。尽管直接使用脉冲神经元易导致模型坍塌和输出噪声，我们设计了一种轮换策略以稳定训练过程，使几何网络在极低计算开销下实现更锐利、更精确的密度分布。我们在合成与真实数据集上进行了广泛实验，结果表明本方法显著提升阈值类方法的性能，为NeRF几何提取提供更鲁棒高效的解决方案。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。