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 NeRF）扩展了NeRF技术，用于对运动场景进行建模。然而，这类模型资源消耗大且难以压缩。针对这一问题，本文提出了WavePlanes——一种快速且更紧凑的显式模型。我们利用N级二维小波系数，构建了多尺度空间及空间-时间特征平面表示。通过逆离散小波变换，可重建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用于近似四维网格中体素的颜色与密度。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，最终模型压缩后大小约为12 MB。与现有最先进的基于平面的模型相比，WavePlanes的模型尺寸缩小高达15倍，计算需求更低，且仅需一小时训练即可达到相当的效果——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，该方案在保持与先前方案同等性能的同时，提供了更强的可解释性。我们的代码发布于：https://github.com/azzarelli/waveplanes/