# A Hierarchical Compression Technique for 3D Gaussian Splatting Compression

arXiv: https://arxiv.org/abs/2411.06976 · HTML: https://mlsanity.com/paper/2411.06976/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 20 references that are in the map.
- First posted on arXiv 11 Nov 2024.

## Builds on (most cited first, 8 of 8)

- [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)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS](https://mlsanity.com/paper/2311.17245/) (2023)
- [HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compression](https://mlsanity.com/paper/2403.14530/) (2024)
- [PKU-DyMVHumans: A Multi-View Video Benchmark for High-Fidelity Dynamic Human Modeling](https://mlsanity.com/paper/2403.16080/) (2024)
- [A Benchmark for Gaussian Splatting Compression and Quality Assessment Study](https://mlsanity.com/paper/2407.14197/) (2024)
- [Explicit-NeRF-QA: A Quality Assessment Database for Explicit NeRF Model Compression](https://mlsanity.com/paper/2407.08165/) (2024)

## Built on by (most cited first, 14 of 14)

- [PCGS: Progressive Compression of 3D Gaussian Splatting](https://mlsanity.com/paper/2503.08511/) (2025)
- [HybridGS: High-Efficiency Gaussian Splatting Data Compression using Dual-Channel Sparse Representation and Point Cloud Encoder](https://mlsanity.com/paper/2505.01938/) (2025)
- [Light4GS: Lightweight Compact 4D Gaussian Splatting Generation via Context Model](https://mlsanity.com/paper/2503.13948/) (2025)
- [ADC-GS: Anchor-Driven Deformable and Compressed Gaussian Splatting for Dynamic Scene Reconstruction](https://mlsanity.com/paper/2505.08196/) (2025)
- [RAP: Fast Feedforward Rendering-Free Attribute-Guided Primitive Importance Score Prediction for Efficient 3D Gaussian Splatting Processing](https://mlsanity.com/paper/2602.19753/) (2026)
- [REFINE: Super-efficient 3D Gaussian Splatting Pruning via Rendering-Free Primitive Importance](https://mlsanity.com/paper/2606.09074/) (2026)
- [AI-Driven Innovations in Volumetric Video Streaming: A Review](https://mlsanity.com/paper/2412.12208/) (2024)
- [A LoD of Gaussians: Unified Training and Rendering for Ultra-Large Scale Reconstruction with External Memory](https://mlsanity.com/paper/2507.01110/) (2025)
- [SUCCESS-GS: Survey of Compactness and Compression for Efficient Static and Dynamic Gaussian Splatting](https://mlsanity.com/paper/2512.07197/) (2025)
- [Lightweight 3D Gaussian Splatting Compression via Video Codec](https://mlsanity.com/paper/2512.11186/) (2025)
- [Learning Hierarchical Sparse Transform Coding for 3DGS Compression](https://mlsanity.com/paper/2505.22908/) (2025)
- [QueryGaussian: Scalable and Training-Free Open-Vocabulary 3D Instance Retrieval](https://mlsanity.com/paper/2606.19733/) (2026)
- [PD-4DGS:Progressive Decomposition of 4D Gaussian Splatting for Bandwidth-Adaptive Dynamic Scene Streaming](https://mlsanity.com/paper/2605.11427/) (2026)
- [Robust, Estimator-Agnostic Dynamic 3DGS Compression](https://mlsanity.com/paper/2609.25633/) (2026)

## Abstract (arXiv)

3D Gaussian Splatting (GS) demonstrates excellent rendering quality and generation speed in novel view synthesis. However, substantial data size poses challenges for storage and transmission, making 3D GS compression an essential technology. Current 3D GS compression research primarily focuses on developing more compact scene representations, such as converting explicit 3D GS data into implicit forms. In contrast, compression of the GS data itself has hardly been explored. To address this gap, we propose a Hierarchical GS Compression (HGSC) technique. Initially, we prune unimportant Gaussians based on importance scores derived from both global and local significance, effectively reducing redundancy while maintaining visual quality. An Octree structure is used to compress 3D positions. Based on the 3D GS Octree, we implement a hierarchical attribute compression strategy by employing a KD-tree to partition the 3D GS into multiple blocks. We apply farthest point sampling to select anchor primitives within each block and others as non-anchor primitives with varying Levels of Details (LoDs). Anchor primitives serve as reference points for predicting non-anchor primitives across different LoDs to reduce spatial redundancy. For anchor primitives, we use the region adaptive hierarchical transform to achieve near-lossless compression of various attributes. For non-anchor primitives, each is predicted based on the k-nearest anchor primitives. To further minimize prediction errors, the reconstructed LoD and anchor primitives are combined to form new anchor primitives to predict the next LoD. Our method notably achieves superior compression quality and a significant data size reduction of over 4.5 times compared to the state-of-the-art compression method on small scenes datasets.