通过频域预滤波提升神经场分辨率，实现快速高效建模。
Spectral Prefiltering of Neural Fields
- 在输入域用傅里叶特征解析调制，实现单次前向传播滤波。
- 支持高斯、盒式、兰克索斯等多种滤波器，训练时无需见过。
- 基于单样本蒙特卡洛估计训练，适配任意网络结构，速度快。
神经场在表示连续视觉信号方面表现优异，但通常以固定分辨率运行。本文提出一种简单而强大的神经场优化方法，可在一次前向传播中完成预滤波。核心创新包括：(1) 通过解析缩放傅里叶特征嵌入的频率响应，在输入域执行卷积滤波；(2) 这种闭式调制可推广至高斯以外的参数化滤波器（如盒式和兰克索斯），且在训练时未见过；(3) 使用单样本蒙特卡洛估计来训练滤波后的信号。该方法在训练和推理阶段均快速，且对网络架构无额外约束。实验表明，其在定量与定性上均优于现有神经场滤波方法。
原文摘要 · Abstract (English)
Neural fields excel at representing continuous visual signals but typically operate at a single, fixed resolution. We present a simple yet powerful method to optimize neural fields that can be prefiltered in a single forward pass. Key innovations and features include: (1) We perform convolutional filtering in the input domain by analytically scaling Fourier feature embeddings with the filter's frequency response. (2) This closed-form modulation generalizes beyond Gaussian filtering and supports other parametric filters (Box and Lanczos) that are unseen at training time. (3) We train the neural field using single-sample Monte Carlo estimates of the filtered signal. Our method is fast during both training and inference, and imposes no additional constraints on the network architecture. We show quantitative and qualitative improvements over existing methods for neural-field filtering.
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。