# NeuralVDB: High-resolution Sparse Volume Representation using Hierarchical Neural Networks

arXiv: https://arxiv.org/abs/2208.04448 · HTML: https://mlsanity.com/paper/2208.04448/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 78 references that are in the map.
- First posted on arXiv 8 Aug 2022.

## Builds on (most cited first, 30 of 31)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Neural Tangent Kernel: Convergence and Generalization in Neural Networks](https://mlsanity.com/paper/1806.07572/) (2018)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [pixelNeRF: Neural Radiance Fields from One or Few Images](https://mlsanity.com/paper/2012.02190/) (2020)
- [On the Spectral Bias of Neural Networks](https://mlsanity.com/paper/1806.08734/) (2018)
- [Learning Implicit Fields for Generative Shape Modeling](https://mlsanity.com/paper/1812.02822/) (2018)
- [Neural Sparse Voxel Fields](https://mlsanity.com/paper/2007.11571/) (2020)
- [Convolutional Occupancy Networks](https://mlsanity.com/paper/2003.04618/) (2020)
- [Neural Fields in Visual Computing and Beyond](https://mlsanity.com/paper/2111.11426/) (2021)
- [Baking Neural Radiance Fields for Real-Time View Synthesis](https://mlsanity.com/paper/2103.14645/) (2021)
- [Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes](https://mlsanity.com/paper/2101.10994/) (2021)
- [MetaSDF: Meta-learning Signed Distance Functions](https://mlsanity.com/paper/2006.09662/) (2020)
- [The Case for Learned Index Structures](https://mlsanity.com/paper/1712.01208/) (2017)
- [Neural Importance Sampling](https://mlsanity.com/paper/1808.03856/) (2018)
- [Finite Basis Physics-Informed Neural Networks (FBPINNs): a scalable domain decomposition approach for solving differential equations](https://mlsanity.com/paper/2107.07871/) (2021)
- [Generative and Discriminative Voxel Modeling with Convolutional Neural Networks](https://mlsanity.com/paper/1608.04236/) (2016)
- [Variable Bitrate Neural Fields](https://mlsanity.com/paper/2206.07707/) (2022)
- [Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completion](https://mlsanity.com/paper/2111.12702/) (2021)
- [Real-time Neural Radiance Caching for Path Tracing](https://mlsanity.com/paper/2106.12372/) (2021)
- [Image and Video Compression with Neural Networks: A Review](https://mlsanity.com/paper/1904.03567/) (2019)
- [Neural Control Variates](https://mlsanity.com/paper/2006.01524/) (2020)
- [Deep Implicit Volume Compression](https://mlsanity.com/paper/2005.08877/) (2020)
- [DeepN-JPEG: A Deep Neural Network Favorable JPEG-based Image Compression Framework](https://mlsanity.com/paper/1803.05788/) (2018)
- [A Robust Volume Conserving Method for Character-Water Interaction](https://mlsanity.com/paper/1902.00801/) (2019)

## Built on by (most cited first, 20 of 20)

- [Don't Splat your Gaussians: Volumetric Ray-Traced Primitives for Modeling and Rendering Scattering and Emissive Media](https://mlsanity.com/paper/2405.15425/) (2024)
- [HyperINR: A Fast and Predictive Hypernetwork for Implicit Neural Representations via Knowledge Distillation](https://mlsanity.com/paper/2304.04188/) (2023)
- [Fluid Simulation on Neural Flow Maps](https://mlsanity.com/paper/2312.14635/) (2023)
- [Distributed Neural Representation for Reactive in situ Visualization](https://mlsanity.com/paper/2304.10516/) (2023)
- [Representing Flow Fields with Divergence-Free Kernels for Reconstruction](https://mlsanity.com/paper/2504.01913/) (2025)
- [Efficient Neural Representation of Volumetric Data using Coordinate-Based Networks](https://mlsanity.com/paper/2401.08840/) (2024)
- [ReFiNe: Recursive Field Networks for Cross-modal Multi-scene Representation](https://mlsanity.com/paper/2406.04309/) (2024)
- [Gabor Fields: Orientation-Selective Level-of-Detail for Volume Rendering](https://mlsanity.com/paper/2602.05081/) (2026)
- [DualBrep: A Dual-Field Continuous Representation for B-rep Modelling](https://mlsanity.com/paper/2606.31579/) (2026)
- [Stochastic Texture Filtering](https://mlsanity.com/paper/2305.05810/) (2023)
- [Hierarchical Autoencoder-based Lossy Compression for Large-scale High-resolution Scientific Data](https://mlsanity.com/paper/2307.04216/) (2023)
- [Improved Stochastic Texture Filtering Through Sample Reuse](https://mlsanity.com/paper/2504.05562/) (2025)
- [Accelerated Volumetric Compression without Hierarchies: A Fourier Feature Based Implicit Neural Representation Approach](https://mlsanity.com/paper/2508.08937/) (2025)
- [Fully-fused Multi-Layer Perceptrons on Intel Data Center GPUs](https://mlsanity.com/paper/2403.17607/) (2024)
- [MozzaVID: Mozzarella Volumetric Image Dataset](https://mlsanity.com/paper/2412.04880/) (2024)
- [INRet: A General Framework for Accurate Retrieval of INRs for Shapes](https://mlsanity.com/paper/2501.15722/) (2025)
- [Collaborative Texture Filtering](https://mlsanity.com/paper/2506.17770/) (2025)
- [Hermite-NGP: Gradient-Augmented Hash Encoding for Learning PDEs](https://mlsanity.com/paper/2605.24774/) (2026)
- [Recent Advances and Trends in Learning-based 3D Representations](https://mlsanity.com/paper/2606.04871/) (2026)
- [3D Field Data Reduction with Adaptive Sample-Based Gaussian-Encoded Reconstruction](https://mlsanity.com/paper/2609.16024/) (2026)

## Abstract (arXiv)

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.