# Compact Neural Graphics Primitives with Learned Hash Probing

arXiv: https://arxiv.org/abs/2312.17241 · HTML: https://mlsanity.com/paper/2312.17241/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 60 references that are in the map.
- First posted on arXiv 28 Dec 2023.

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

- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Magic3D: High-Resolution Text-to-3D Content Creation](https://mlsanity.com/paper/2211.10440/) (2022)
- [Neural Sparse Voxel Fields](https://mlsanity.com/paper/2007.11571/) (2020)
- [PlenOctrees for Real-time Rendering of Neural Radiance Fields](https://mlsanity.com/paper/2103.14024/) (2021)
- [Convolutional Occupancy Networks](https://mlsanity.com/paper/2003.04618/) (2020)
- [K-Planes: Explicit Radiance Fields in Space, Time, and Appearance](https://mlsanity.com/paper/2301.10241/) (2023)
- [Neural Fields in Visual Computing and Beyond](https://mlsanity.com/paper/2111.11426/) (2021)
- [Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes](https://mlsanity.com/paper/2101.10994/) (2021)
- [From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification](https://mlsanity.com/paper/1602.02068/) (2016)
- [Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction](https://mlsanity.com/paper/2003.10983/) (2020)
- [Lossy Image Compression with Compressive Autoencoders](https://mlsanity.com/paper/1703.00395/) (2017)
- [COIN: COmpression with Implicit Neural representations](https://mlsanity.com/paper/2103.03123/) (2021)
- [Sparse Sequence-to-Sequence Models](https://mlsanity.com/paper/1905.05702/) (2019)
- [Implicit Neural Representations for Image Compression](https://mlsanity.com/paper/2112.04267/) (2021)
- [BACON: Band-limited Coordinate Networks for Multiscale Scene Representation](https://mlsanity.com/paper/2112.04645/) (2021)
- [Variable Bitrate Neural Fields](https://mlsanity.com/paper/2206.07707/) (2022)
- [Real-time Neural Radiance Caching for Path Tracing](https://mlsanity.com/paper/2106.12372/) (2021)
- [COIN++: Neural Compression Across Modalities](https://mlsanity.com/paper/2201.12904/) (2022)
- [Compressing Volumetric Radiance Fields to 1 MB](https://mlsanity.com/paper/2211.16386/) (2022)
- [Gradient Estimation with Stochastic Softmax Tricks](https://mlsanity.com/paper/2006.08063/) (2020)
- [ACORN: Adaptive Coordinate Networks for Neural Scene Representation](https://mlsanity.com/paper/2105.02788/) (2021)
- [Compressive Neural Representations of Volumetric Scalar Fields](https://mlsanity.com/paper/2104.04523/) (2021)
- [Learned Point Cloud Geometry Compression](https://mlsanity.com/paper/1909.12037/) (2019)
- [Deep Implicit Volume Compression](https://mlsanity.com/paper/2005.08877/) (2020)
- [Random-Access Neural Compression of Material Textures](https://mlsanity.com/paper/2305.17105/) (2023)
- [LVAC: Learned Volumetric Attribute Compression for Point Clouds using Coordinate Based Networks](https://mlsanity.com/paper/2111.08988/) (2021)
- [DropMax: Adaptive Variational Softmax](https://mlsanity.com/paper/1712.07834/) (2017)

## Built on by (most cited first, 19 of 19)

- [Instant GaussianImage: A Generalizable and Self-Adaptive Image Representation via 2D Gaussian Splatting](https://mlsanity.com/paper/2506.23479/) (2025)
- [Neural Shell Texture Splatting: More Details and Fewer Primitives](https://mlsanity.com/paper/2507.20200/) (2025)
- [What You See is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANs](https://mlsanity.com/paper/2401.02411/) (2024)
- [Stochastic Preconditioning for Neural Field Optimization](https://mlsanity.com/paper/2505.20473/) (2025)
- [CodecNeRF: Toward Fast Encoding and Decoding, Compact, and High-quality Novel-view Synthesis](https://mlsanity.com/paper/2404.04913/) (2024)
- [Volumetric Surfaces: Representing Fuzzy Geometries with Layered Meshes](https://mlsanity.com/paper/2409.02482/) (2024)
- [Lagrangian Hashing for Compressed Neural Field Representations](https://mlsanity.com/paper/2409.05334/) (2024)
- [Neural Harmonic Textures for High-Quality Primitive Based Neural Reconstruction](https://mlsanity.com/paper/2604.01204/) (2026)
- [Vertex Features for Neural Global Illumination](https://mlsanity.com/paper/2508.07852/) (2025)
- [2D Neural Fields with Learned Discontinuities](https://mlsanity.com/paper/2408.00771/) (2024)
- [Plenoptic PNG: Real-Time Neural Radiance Fields in 150 KB](https://mlsanity.com/paper/2409.15689/) (2024)
- [Low-Rank Adaptation of Neural Fields](https://mlsanity.com/paper/2504.15933/) (2025)
- [A New Perspective To Understanding Multi-resolution Hash Encoding For Neural Fields](https://mlsanity.com/paper/2505.03042/) (2025)
- [EUGens: Efficient, Unified, and General Dense Layers](https://mlsanity.com/paper/2601.22563/) (2026)
- [D'OH: Decoder-Only Random Hypernetworks for Implicit Neural Representations](https://mlsanity.com/paper/2403.19163/) (2024)
- [NESI: Shape Representation via Neural Explicit Surface Intersection](https://mlsanity.com/paper/2409.06030/) (2024)
- [EUGens: Efficient, Unified, and General Dense Layers](https://mlsanity.com/paper/2410.09771/) (2024)
- [Self-Supervised Multi-Modal World Model with 4D Space-Time Embedding](https://mlsanity.com/paper/2603.07039/) (2026)
- [CARA: Collision-Aware Resolution Adaptation for Multiresolution Hash Encoding Based Image Fitting](https://mlsanity.com/paper/2609.18554/) (2026)

## Abstract (arXiv)

Neural graphics primitives are faster and achieve higher quality when their neural networks are augmented by spatial data structures that hold trainable features arranged in a grid. However, existing feature grids either come with a large memory footprint (dense or factorized grids, trees, and hash tables) or slow performance (index learning and vector quantization). In this paper, we show that a hash table with learned probes has neither disadvantage, resulting in a favorable combination of size and speed. Inference is faster than unprobed hash tables at equal quality while training is only 1.2-2.6x slower, significantly outperforming prior index learning approaches. We arrive at this formulation by casting all feature grids into a common framework: they each correspond to a lookup function that indexes into a table of feature vectors. In this framework, the lookup functions of existing data structures can be combined by simple arithmetic combinations of their indices, resulting in Pareto optimal compression and speed.