We introduce NeuralVDB, which improves on an existing industry standard for efficient storage of sparse volumetric data, denoted VDB [Museth 2013], by leveraging recent advancements in machine learning. Our novel hybrid data structure can reduce the memory footprints of VDB volumes by orders of magnitude, while maintaining its flexibility and only incurring small (user-controlled) compression errors. Specifically, NeuralVDB replaces the lower nodes of a shallow and wide VDB tree structure with multiple hierarchical neural networks that separately encode topology and value information by means of neural classifiers and regressors respectively. This approach is proven to maximize the compression ratio while maintaining the spatial adaptivity offered by the higher-level VDB data structure. For sparse signed distance fields and density volumes, we have observed compression ratios on the order of 10x to more than 100x from already compressed VDB inputs, with little to no visual artifacts. Furthermore, NeuralVDB is shown to offer more effective compression performance compared to other neural representations such as Neural Geometric Level of Detail [Takikawa et al. 2021], Variable Bitrate Neural Fields [Takikawa et al. 2022a], and Instant Neural Graphics Primitives [M\"uller et al. 2022]. Finally, we demonstrate how warm-starting from previous frames can accelerate training, i.e., compression, of animated volumes as well as improve temporal coherency of model inference, i.e., decompression.

翻译：我们提出NeuralVDB，它通过利用机器学习的最新进展，改进了现有用于高效存储稀疏体数据的行业标准VDB [Museth 2013]。这种新颖的混合数据结构可将VDB体的内存占用减少数个数量级，同时保持其灵活性且仅引入较小的（用户可控）压缩误差。具体而言，NeuralVDB用多个分层神经网络替代浅而宽的VDB树结构中的低层节点，这些神经网络分别通过神经分类器和回归器对拓扑信息和数值信息进行编码。该方法经证明可在保持高层VDB数据结构提供的空间自适应性的同时最大化压缩比。对于稀疏有符号距离场和密度体，我们观察到从已压缩的VDB输入可达到10倍至超过100倍的压缩比，且几乎没有视觉伪影。此外，与神经几何细节层次[Takikawa等人，2021]、可变比特率神经场[Takikawa等人，2022a]和即时神经图形基元[Müller等人，2022]等其他神经表示相比，NeuralVDB提供了更有效的压缩性能。最后，我们展示了如何通过前帧热启动来加速动画体的训练（即压缩）过程，同时提升模型推理（即解压缩）的时间连贯性。