Dynamic Neural Radiance Fields (Dynamic NeRF) enhance NeRF technology to
model moving scenes. However, they are resource intensive and challenging to
compress. To address this issue, this paper presents WavePlanes, a fast and
more compact explicit model. We propose a multi-scale space and space-time
feature plane representation using N-level 2-D wavelet coefficients. The
inverse discrete wavelet transform reconstructs N feature signals at varying
detail, which are linearly decoded to approximate the color and density of
volumes in a 4-D grid. Exploiting the sparsity of wavelet coefficients, we
compress a Hash Map containing only non-zero coefficients and their locations
on each plane. This results in a compressed model size of ~12 MB. Compared with
state-of-the-art plane-based models, WavePlanes is up to 15x smaller, less
computationally demanding and achieves comparable results in as little as one
hour of training - without requiring custom CUDA code or high performance
computing resources. Additionally, we propose new feature fusion schemes that
work as well as previously proposed schemes while providing greater
interpretability. Our code is available at:
this https URL

Dynamic Neural Radiance Fields（Dynamic NeRF）提升了 NeRF 技术以对移动场景建模，然而，它们需要大量资源且难以压缩。为解决该问题，本文提出了 WavePlanes，一种更快且更紧凑的显式模型。我们提出了一个多尺度空间和时空特征平面表示，使用 N 级 2D 小波系数。逆离散小波变换重构了 N 个特征信号，具有不同的细节，线性解码以近似 4D 网格中体积的颜色和密度。利用小波系数的稀疏性，我们压缩了一个哈希映射，仅包含非零系数及其在每个平面上的位置。这导致压缩模型大小约为 12 MB。与最先进的基于平面的模型相比，WavePlanes 小了多达 15 倍，计算需求较低，并在仅一个小时的训练内实现了可比拟的结果 - 无需定制 CUDA 代码或高性能计算资源。此外，我们提出了新的特征融合方案，其效果不亚于以前提出的方案，同时提供更大的可解释性。我们的代码位于：this https URL

WavePlanes: 动态神经辐射场的紧凑小波表示

WavePlanes: A compact Wavelet representation for Dynamic Neural Radiance  Fields

A framework is proposed for the unconditional generation of synthetic time
series based on learning from a single sample in low-data regime case. The
framework aims at capturing the distribution of patches in wavelet scalogram of
time series using single image generative models and producing realistic
wavelet coefficients for the generation of synthetic time series. It is
demonstrated that the framework is effective with respect to fidelity and
diversity for time series with insignificant to no trends. Also, the
performance is more promising for generating samples with the same duration
(reshuffling) rather than longer ones (retargeting).

本研究提出了一种从单一样本中学习生成低数据制度下合成时间序列的框架，它利用单个图像生成模型捕捉时间序列波小波形成对数分布，为生成合成时间序列绘制逼真的波小波系数。结果显示这个框架对于在无趋势的时间序列中保证了逼真度和多样性，而且生成的样本时长相同时（重新混洗），其性能更加优秀。