# FlexGaussian: Flexible and Cost-Effective Training-Free Compression for 3D Gaussian Splatting

arXiv: https://arxiv.org/abs/2507.06671 · HTML: https://mlsanity.com/paper/2507.06671/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 45 references that are in the map.
- First posted on arXiv 9 Jul 2025.

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

- [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)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering](https://mlsanity.com/paper/2312.00109/) (2023)
- [HAQ: Hardware-Aware Automated Quantization with Mixed Precision](https://mlsanity.com/paper/1811.08886/) (2018)
- [LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS](https://mlsanity.com/paper/2311.17245/) (2023)
- [HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision](https://mlsanity.com/paper/1905.03696/) (2019)
- [Compact 3D Gaussian Representation for Radiance Field](https://mlsanity.com/paper/2311.13681/) (2023)
- [Slimmable Neural Networks](https://mlsanity.com/paper/1812.08928/) (2018)
- [Universally Slimmable Networks and Improved Training Techniques](https://mlsanity.com/paper/1903.05134/) (2019)
- [HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compression](https://mlsanity.com/paper/2403.14530/) (2024)
- [EAGLES: Efficient Accelerated 3D Gaussians with Lightweight EncodingS](https://mlsanity.com/paper/2312.04564/) (2023)
- [MatrixCity: A Large-scale City Dataset for City-scale Neural Rendering and Beyond](https://mlsanity.com/paper/2309.16553/) (2023)
- [Reducing the Memory Footprint of 3D Gaussian Splatting](https://mlsanity.com/paper/2406.17074/) (2024)
- [CompGS: Smaller and Faster Gaussian Splatting with Vector Quantization](https://mlsanity.com/paper/2311.18159/) (2023)
- [Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search](https://mlsanity.com/paper/1812.00090/) (2018)
- [Compressible-composable NeRF via Rank-residual Decomposition](https://mlsanity.com/paper/2205.14870/) (2022)
- [Dynamic Slimmable Network](https://mlsanity.com/paper/2103.13258/) (2021)
- [End-to-End Rate-Distortion Optimized 3D Gaussian Representation](https://mlsanity.com/paper/2406.01597/) (2024)
- [MesonGS: Post-training Compression of 3D Gaussians via Efficient Attribute Transformation](https://mlsanity.com/paper/2409.09756/) (2024)
- [DOGS: Distributed-Oriented Gaussian Splatting for Large-Scale 3D Reconstruction Via Gaussian Consensus](https://mlsanity.com/paper/2405.13943/) (2024)
- [On Scaling Up 3D Gaussian Splatting Training](https://mlsanity.com/paper/2406.18533/) (2024)
- [Trimming the Fat: Efficient Compression of 3D Gaussian Splats through Pruning](https://mlsanity.com/paper/2406.18214/) (2024)
- [Slimmable Generative Adversarial Networks](https://mlsanity.com/paper/2012.05660/) (2020)
- [MetaSapiens: Real-Time Neural Rendering with Efficiency-Aware Pruning and Accelerated Foveated Rendering](https://mlsanity.com/paper/2407.00435/) (2024)
- [RetinaGS: Scalable Training for Dense Scene Rendering with Billion-Scale 3D Gaussians](https://mlsanity.com/paper/2406.11836/) (2024)
- [Mesorasi: Architecture Support for Point Cloud Analytics via Delayed-Aggregation](https://mlsanity.com/paper/2008.06967/) (2020)
- [Tigris: Architecture and Algorithms for 3D Perception in Point Clouds](https://mlsanity.com/paper/1911.07841/) (2019)

## Built on by (most cited first, 11 of 11)

- [ExGS: Extreme 3D Gaussian Compression with Diffusion Priors](https://mlsanity.com/paper/2509.24758/) (2025)
- [Matryoshka Gaussian Splatting](https://mlsanity.com/paper/2603.19234/) (2026)
- [Local-GS: Accelerating 3D Gaussian Splatting via Tile-Local Warp Coherence](https://mlsanity.com/paper/2606.16566/) (2026)
- [3DTurboQuant: Training-Free Near-Optimal Quantization for 3D Reconstruction Models](https://mlsanity.com/paper/2604.05366/) (2026)
- [MesonGS++: Post-training Compression of 3D Gaussian Splatting with Hyperparameter Searching](https://mlsanity.com/paper/2604.26799/) (2026)
- [VEDAL: Variational Error-Driven Asynchronous Learning for 3D Gaussian Splatting Pruning](https://mlsanity.com/paper/2606.02346/) (2026)
- [Robust, Estimator-Agnostic Dynamic 3DGS Compression](https://mlsanity.com/paper/2609.25633/) (2026)
- [Only What Was Seen: Observation-Gram Compaction of View-Dependent Appearance in 3D Gaussian Splatting](https://mlsanity.com/paper/2609.28997/) (2026)
- [Towards Practical Compression of 3D Gaussian Splatting](https://mlsanity.com/paper/2609.30245/) (2026)
- [TSGL: Teacher-Student Graph Learning for 3DGS Compression](https://mlsanity.com/paper/2609.38635/) (2026)
- [Efficient Gaussian Splatting Sequence Compression with Standard Video Codecs](https://mlsanity.com/paper/2610.07795/) (2026)

## Abstract (arXiv)

3D Gaussian splatting has become a prominent technique for representing and rendering complex 3D scenes, due to its high fidelity and speed advantages. However, the growing demand for large-scale models calls for effective compression to reduce memory and computation costs, especially on mobile and edge devices with limited resources. Existing compression methods effectively reduce 3D Gaussian parameters but often require extensive retraining or fine-tuning, lacking flexibility under varying compression constraints. In this paper, we introduce FlexGaussian, a flexible and cost-effective method that combines mixed-precision quantization with attribute-discriminative pruning for training-free 3D Gaussian compression. FlexGaussian eliminates the need for retraining and adapts easily to diverse compression targets. Evaluation results show that FlexGaussian achieves up to 96.4% compression while maintaining high rendering quality (<1 dB drop in PSNR), and is deployable on mobile devices. FlexGaussian delivers high compression ratios within seconds, being 1.7-2.1x faster than state-of-the-art training-free methods and 10-100x faster than training-involved approaches. The code is being prepared and will be released soon at: https://github.com/Supercomputing-System-AI-Lab/FlexGaussian