# CompGS: Smaller and Faster Gaussian Splatting with Vector Quantization

arXiv: https://arxiv.org/abs/2311.18159 · HTML: https://mlsanity.com/paper/2311.18159/

## Key facts

- Cited by 130 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 64 references that are in the map.
- First posted on arXiv 30 Nov 2023.

## Builds on (most cited first, 30 of 47)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [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)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [TensoRF: Tensorial Radiance Fields](https://mlsanity.com/paper/2203.09517/) (2022)
- [Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction](https://mlsanity.com/paper/2111.11215/) (2021)
- [LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale](https://mlsanity.com/paper/2208.07339/) (2022)
- [PlenOctrees for Real-time Rendering of Neural Radiance Fields](https://mlsanity.com/paper/2103.14024/) (2021)
- [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://mlsanity.com/paper/1603.05279/) (2016)
- [Vector Quantized Diffusion Model for Text-to-Image Synthesis](https://mlsanity.com/paper/2111.14822/) (2021)
- [KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs](https://mlsanity.com/paper/2103.13744/) (2021)
- [Learning Structured Sparsity in Deep Neural Networks](https://mlsanity.com/paper/1608.03665/) (2016)
- [Quantizing deep convolutional networks for efficient inference: A whitepaper](https://mlsanity.com/paper/1806.08342/) (2018)
- [FastNeRF: High-Fidelity Neural Rendering at 200FPS](https://mlsanity.com/paper/2103.10380/) (2021)
- [Point-NeRF: Point-based Neural Radiance Fields](https://mlsanity.com/paper/2201.08845/) (2022)
- [Do Deep Nets Really Need to be Deep?](https://mlsanity.com/paper/1312.6184/) (2013)
- [Baking Neural Radiance Fields for Real-Time View Synthesis](https://mlsanity.com/paper/2103.14645/) (2021)
- [ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data](https://mlsanity.com/paper/2111.08897/) (2021)
- [LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS](https://mlsanity.com/paper/2311.17245/) (2023)
- [DeepVoxels: Learning Persistent 3D Feature Embeddings](https://mlsanity.com/paper/1812.01024/) (2018)
- [Deep Learning with Limited Numerical Precision](https://mlsanity.com/paper/1502.02551/) (2015)
- [Compact 3D Gaussian Representation for Radiance Field](https://mlsanity.com/paper/2311.13681/) (2023)
- [MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures](https://mlsanity.com/paper/2208.00277/) (2022)
- [Model compression via distillation and quantization](https://mlsanity.com/paper/1802.05668/) (2018)

## Built on by (most cited first, 30 of 130)

- [3D Gaussian Splatting: Survey, Technologies, Challenges, and Opportunities](https://mlsanity.com/paper/2407.17418/) (2024)
- [MEGA: Memory-Efficient 4D Gaussian Splatting for Dynamic Scenes](https://mlsanity.com/paper/2410.13613/) (2024)
- [MaskGaussian: Adaptive 3D Gaussian Representation from Probabilistic Masks](https://mlsanity.com/paper/2412.20522/) (2024)
- [LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPS](https://mlsanity.com/paper/2507.07136/) (2025)
- [Textured Gaussians for Enhanced 3D Scene Appearance Modeling](https://mlsanity.com/paper/2411.18625/) (2024)
- [GaussianSpa: An "Optimizing-Sparsifying" Simplification Framework for Compact and High-Quality 3D Gaussian Splatting](https://mlsanity.com/paper/2411.06019/) (2024)
- [4DGC: Rate-Aware 4D Gaussian Compression for Efficient Streamable Free-Viewpoint Video](https://mlsanity.com/paper/2503.18421/) (2025)
- [3DGR-CT: Sparse-View CT Reconstruction with a 3D Gaussian Representation](https://mlsanity.com/paper/2312.15676/) (2023)
- [Locality-aware Gaussian Compression for Fast and High-quality Rendering](https://mlsanity.com/paper/2501.05757/) (2025)
- [HiMoR: Monocular Deformable Gaussian Reconstruction with Hierarchical Motion Representation](https://mlsanity.com/paper/2504.06210/) (2025)
- [Gaussian Eigen Models for Human Heads](https://mlsanity.com/paper/2407.04545/) (2024)
- [Generalized and Efficient 2D Gaussian Splatting for Arbitrary-scale Super-Resolution](https://mlsanity.com/paper/2501.06838/) (2025)
- [StreetSurfGS: Scalable Urban Street Surface Reconstruction with Planar-based Gaussian Splatting](https://mlsanity.com/paper/2410.04354/) (2024)
- [Optimized Minimal 3D Gaussian Splatting](https://mlsanity.com/paper/2503.16924/) (2025)
- [Advancing Extended Reality with 3D Gaussian Splatting: Innovations and Prospects](https://mlsanity.com/paper/2412.06257/) (2024)
- [Efficient Scene Modeling via Structure-Aware and Region-Prioritized 3D Gaussians](https://mlsanity.com/paper/2411.12788/) (2024)
- [Neural Shell Texture Splatting: More Details and Fewer Primitives](https://mlsanity.com/paper/2507.20200/) (2025)
- [1000+ FPS 4D Gaussian Splatting for Dynamic Scene Rendering](https://mlsanity.com/paper/2503.16422/) (2025)
- [Balanced 3DGS: Gaussian-wise Parallelism Rendering with Fine-Grained Tiling](https://mlsanity.com/paper/2412.17378/) (2024)
- [Temporally Compressed 3D Gaussian Splatting for Dynamic Scenes](https://mlsanity.com/paper/2412.05700/) (2024)
- [GoDe: Gaussians on Demand for Progressive Level of Detail and Scalable Compression](https://mlsanity.com/paper/2501.13558/) (2025)
- [GSCodec Studio: A Modular Framework for Gaussian Splat Compression](https://mlsanity.com/paper/2506.01822/) (2025)
- [FlexGaussian: Flexible and Cost-Effective Training-Free Compression for 3D Gaussian Splatting](https://mlsanity.com/paper/2507.06671/) (2025)
- [Hardware-Rasterized Ray-Based Gaussian Splatting](https://mlsanity.com/paper/2503.18682/) (2025)
- [SPARS3R: Semantic Prior Alignment and Regularization for Sparse 3D Reconstruction](https://mlsanity.com/paper/2411.12592/) (2024)
- [Turbo-GS: Accelerating 3D Gaussian Fitting for High-Quality Radiance Fields](https://mlsanity.com/paper/2412.13547/) (2024)
- [CLoD-GS: Continuous Level-of-Detail via 3D Gaussian Splatting](https://mlsanity.com/paper/2510.09997/) (2025)
- [Multi-Layer Gaussian Splatting for Immersive Anatomy Visualization](https://mlsanity.com/paper/2410.16978/) (2024)
- [NexusSplats: Efficient 3D Gaussian Splatting in the Wild](https://mlsanity.com/paper/2411.14514/) (2024)
- [SizeGS: Size-aware Compression of 3D Gaussian Splatting via Mixed Integer Programming](https://mlsanity.com/paper/2412.05808/) (2024)

## Abstract (arXiv)

3D Gaussian Splatting (3DGS) is a new method for modeling and rendering 3D radiance fields that achieves much faster learning and rendering time compared to SOTA NeRF methods. However, it comes with a drawback in the much larger storage demand compared to NeRF methods since it needs to store the parameters for several 3D Gaussians. We notice that many Gaussians may share similar parameters, so we introduce a simple vector quantization method based on K-means to quantize the Gaussian parameters while optimizing them. Then, we store the small codebook along with the index of the code for each Gaussian. We compress the indices further by sorting them and using a method similar to run-length encoding. Moreover, we use a simple regularizer to encourage zero opacity (invisible Gaussians) to reduce the storage and rendering time by a large factor through reducing the number of Gaussians. We do extensive experiments on standard benchmarks as well as an existing 3D dataset that is an order of magnitude larger than the standard benchmarks used in this field. We show that our simple yet effective method can reduce the storage cost for 3DGS by 40 to 50x and rendering time by 2 to 3x with a very small drop in the quality of rendered images.