# HEMGS: A Hybrid Entropy Model for 3D Gaussian Splatting Data Compression

arXiv: https://arxiv.org/abs/2411.18473 · HTML: https://mlsanity.com/paper/2411.18473/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 42 references that are in the map.
- First posted on arXiv 27 Nov 2024.

## Builds on (most cited first, 29 of 29)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018)
- [Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering](https://mlsanity.com/paper/2312.00109/) (2023)
- [Joint Autoregressive and Hierarchical Priors for Learned Image Compression](https://mlsanity.com/paper/1809.02736/) (2018)
- [Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules](https://mlsanity.com/paper/2001.01568/) (2020)
- [LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS](https://mlsanity.com/paper/2311.17245/) (2023)
- [Compact 3D Gaussian Representation for Radiance Field](https://mlsanity.com/paper/2311.13681/) (2023)
- [DVC: An End-to-end Deep Video Compression Framework](https://mlsanity.com/paper/1812.00101/) (2018)
- [Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesis](https://mlsanity.com/paper/2401.02436/) (2023)
- [Deep Contextual Video Compression](https://mlsanity.com/paper/2109.15047/) (2021)
- [HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compression](https://mlsanity.com/paper/2403.14530/) (2024)
- [Checkerboard Context Model for Efficient Learned Image Compression](https://mlsanity.com/paper/2103.15306/) (2021)
- [EAGLES: Efficient Accelerated 3D Gaussians with Lightweight EncodingS](https://mlsanity.com/paper/2312.04564/) (2023)
- [FVC: A New Framework towards Deep Video Compression in Feature Space](https://mlsanity.com/paper/2105.09600/) (2021)
- [Compact 3D Scene Representation via Self-Organizing Gaussian Grids](https://mlsanity.com/paper/2312.13299/) (2023)
- [Reducing the Memory Footprint of 3D Gaussian Splatting](https://mlsanity.com/paper/2406.17074/) (2024)
- [Entroformer: A Transformer-based Entropy Model for Learned Image Compression](https://mlsanity.com/paper/2202.05492/) (2022)
- [ContextGS: Compact 3D Gaussian Splatting with Anchor Level Context Model](https://mlsanity.com/paper/2405.20721/) (2024)
- [Differentiable Point-Based Radiance Fields for Efficient View Synthesis](https://mlsanity.com/paper/2205.14330/) (2022)
- [CompGS: Efficient 3D Scene Representation via Compressed Gaussian Splatting](https://mlsanity.com/paper/2404.09458/) (2024)
- [Improving Deep Video Compression by Resolution-adaptive Flow Coding](https://mlsanity.com/paper/2009.05982/) (2020)
- [Learning Accurate Entropy Model with Global Reference for Image Compression](https://mlsanity.com/paper/2010.08321/) (2020)
- [CRA5: Extreme Compression of ERA5 for Portable Global Climate and Weather Research via an Efficient Variational Transformer](https://mlsanity.com/paper/2405.03376/) (2024)
- [Group-aware Parameter-efficient Updating for Content-Adaptive Neural Video Compression](https://mlsanity.com/paper/2405.04274/) (2024)
- [Towards Point Cloud Compression for Machine Perception: A Simple and Strong Baseline by Learning the Octree Depth Level Predictor](https://mlsanity.com/paper/2406.00791/) (2024)

## Built on by (most cited first, 30 of 31)

- [HAC++: Towards 100X Compression of 3D Gaussian Splatting](https://mlsanity.com/paper/2501.12255/) (2025)
- [PCGS: Progressive Compression of 3D Gaussian Splatting](https://mlsanity.com/paper/2503.08511/) (2025)
- [GSCodec Studio: A Modular Framework for Gaussian Splat Compression](https://mlsanity.com/paper/2506.01822/) (2025)
- [SizeGS: Size-aware Compression of 3D Gaussian Splatting via Mixed Integer Programming](https://mlsanity.com/paper/2412.05808/) (2024)
- [D-FCGS: Feedforward Compression of Dynamic Gaussian Splatting for Free-Viewpoint Videos](https://mlsanity.com/paper/2507.05859/) (2025)
- [3D Gaussian Splatting Data Compression with Mixture of Priors](https://mlsanity.com/paper/2505.03310/) (2025)
- [MEGS2: Memory-Efficient Gaussian Splatting via Spherical Gaussians and Unified Pruning](https://mlsanity.com/paper/2509.07021/) (2025)
- [Improving 3D Gaussian Splatting Compression by Scene-Adaptive Lattice Vector Quantization](https://mlsanity.com/paper/2509.13482/) (2025)
- [Feed-Forward 3D Gaussian Splatting Compression with Long-Context Modeling](https://mlsanity.com/paper/2512.00877/) (2025)
- [CAT-3DGS Pro: A New Benchmark for Efficient 3DGS Compression](https://mlsanity.com/paper/2503.12862/) (2025)
- [TED-4DGS: Temporally Activated and Embedding-based Deformation for 4DGS Compression](https://mlsanity.com/paper/2512.05446/) (2025)
- [ECoNGS: Efficient Compressive Neural Gaussian Splats for Volume Visualization](https://mlsanity.com/paper/2607.18466/) (2026)
- [SUCCESS-GS: Survey of Compactness and Compression for Efficient Static and Dynamic Gaussian Splatting](https://mlsanity.com/paper/2512.07197/) (2025)
- [NanoGS: Training-Free Gaussian Splat Simplification](https://mlsanity.com/paper/2603.16103/) (2026)
- [GSta: Efficient Training Scheme with Siestaed Gaussians for Monocular 3D Scene Reconstruction](https://mlsanity.com/paper/2504.06716/) (2025)
- [Learning Hierarchical Sparse Transform Coding for 3DGS Compression](https://mlsanity.com/paper/2505.22908/) (2025)
- [Smol-GS: Compact Representations for Abstract 3D Gaussian Splatting](https://mlsanity.com/paper/2512.00850/) (2025)
- [P-4DGS: Predictive 4D Gaussian Splatting with 90× Compression](https://mlsanity.com/paper/2510.10030/) (2025)
- [CSGaussian: Progressive Rate-Distortion Compression and Segmentation for 3D Gaussian Splatting](https://mlsanity.com/paper/2601.12814/) (2026)
- [Lightweight High-Fidelity Low-Bitrate Talking Face Compression for 3D Video Conference](https://mlsanity.com/paper/2601.21269/) (2026)
- [Nix and Fix: Targeting 1000x Compression of 3D Gaussian Splatting with Diffusion Models](https://mlsanity.com/paper/2602.04549/) (2026)
- [LG-HCC: Local Geometry-Aware Hierarchical Context Compression for 3D Gaussian Splatting](https://mlsanity.com/paper/2603.28431/) (2026)
- [Unfolding 3D Gaussian Splatting via Iterative Gaussian Synopsis](https://mlsanity.com/paper/2604.11685/) (2026)
- [MesonGS++: Post-training Compression of 3D Gaussian Splatting with Hyperparameter Searching](https://mlsanity.com/paper/2604.26799/) (2026)
- [PD-4DGS:Progressive Decomposition of 4D Gaussian Splatting for Bandwidth-Adaptive Dynamic Scene Streaming](https://mlsanity.com/paper/2605.11427/) (2026)
- [Seeing What Matters: Perceptual Wrapper with Common Randomness for 3D Gaussian Splatting](https://mlsanity.com/paper/2606.11782/) (2026)
- [M3ISR: A Multi-Modal Multi-View Benchmark for 3D/4D Gaussian Splatting and Feedforward Compression](https://mlsanity.com/paper/2608.22465/) (2026)
- [KISS-GS: 3D Gaussian Splatting Compression Kept Simple](https://mlsanity.com/paper/2608.26948/) (2026)
- [Compressing 3D Gaussian Splatting via Cross-Representation Priors](https://mlsanity.com/paper/2609.23005/) (2026)
- [Only What Was Seen: Observation-Gram Compaction of View-Dependent Appearance in 3D Gaussian Splatting](https://mlsanity.com/paper/2609.28997/) (2026)

## Abstract (arXiv)

In this work, we propose a novel compression framework for 3D Gaussian Splatting (3DGS) data. Building on anchor-based 3DGS methodologies, our approach compresses all attributes within each anchor by introducing a novel Hybrid Entropy Model for 3D Gaussian Splatting (HEMGS) to achieve hybrid lossy-lossless compression. It consists of three main components: a variable-rate predictor, a hyperprior network, and an autoregressive network. First, unlike previous methods that adopt multiple models to achieve multi-rate lossy compression, thereby increasing training overhead, our variable-rate predictor enables variable-rate compression with a single model and a hyperparameter λ by producing a learned Quantization Step feature for versatile lossy compression. Second, to improve lossless compression, the hyperprior network captures both scene-agnostic and scene-specific features to generate a prior feature, while the autoregressive network employs an adaptive context selection algorithm with flexible receptive fields to produce a contextual feature. By integrating these two features, HEMGS can accurately estimate the distribution of the current coding element within each attribute, enabling improved entropy coding and reduced storage. We integrate HEMGS into a compression framework, and experimental results on four benchmarks indicate that HEMGS achieves about a 40% average reduction in size while maintaining rendering quality over baseline methods and achieving state-of-the-art compression results.