论文标题
QFF：量化神经场表示的傅立叶特征
QFF: Quantized Fourier Features for Neural Field Representations
论文作者
论文摘要
多层感知器（MLP）缓慢学习高频。最近的方法编码空间箱中的特征，以提高学习速度的详细信息，但以更大的模型大小和连续性损失为代价。取而代之的是，我们建议在通常用于位置编码的傅立叶功能的箱中编码功能。我们称这些量化的傅立叶功能（QFF）。作为一种自然的多解析和周期性表示，我们的实验表明，使用QFF会导致较小的模型大小，更快的训练和更好的质量输出，包括神经图像表示（NIR），神经辐射场（NERF）和签名距离功能（SDF）模型。 QFF易于编码，快速计算，并用作许多神经场表示的简单添加。
Multilayer perceptrons (MLPs) learn high frequencies slowly. Recent approaches encode features in spatial bins to improve speed of learning details, but at the cost of larger model size and loss of continuity. Instead, we propose to encode features in bins of Fourier features that are commonly used for positional encoding. We call these Quantized Fourier Features (QFF). As a naturally multiresolution and periodic representation, our experiments show that using QFF can result in smaller model size, faster training, and better quality outputs for several applications, including Neural Image Representations (NIR), Neural Radiance Field (NeRF) and Signed Distance Function (SDF) modeling. QFF are easy to code, fast to compute, and serve as a simple drop-in addition to many neural field representations.
