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: https://github.com/azzarelli/waveplanes/

翻译：动态神经辐射场（Dynamic Neural Radiance Fields，Dynamic NeRF）增强了NeRF技术对运动场景的建模能力。然而，该类模型资源消耗大且难以压缩。为解决此问题，本文提出WavePlanes——一种更快速、更紧凑的显式模型。我们提出一种基于N级二维小波系数的多尺度空间与时空特征平面表示法。通过逆离散小波变换重构出具有不同细节层次的N个特征信号，这些信号经线性解码后近似表示四维网格体素的颜色与密度。利用小波系数的稀疏性，我们对仅包含非零系数及其平面位置的哈希映射进行压缩，最终得到约12 MB的压缩模型尺寸。与基于平面的最新模型相比，WavePlanes的体积缩小高达15倍，计算需求更低，且仅需一小时训练即可达到相当性能——无需自定义CUDA代码或高性能计算资源。此外，我们提出新的特征融合方案，在保持可解释性的同时达到与先前方案同等效果。代码开源地址：https://github.com/azzarelli/waveplanes/