# SizeGS: Size-aware Compression of 3D Gaussian Splatting via Mixed Integer Programming

arXiv: https://arxiv.org/abs/2412.05808 · HTML: https://mlsanity.com/paper/2412.05808/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 64 references that are in the map.
- First posted on arXiv 8 Dec 2024.

## Builds on (most cited first, 30 of 35)

- [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)
- [Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction](https://mlsanity.com/paper/2111.11215/) (2021)
- [Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering](https://mlsanity.com/paper/2312.00109/) (2023)
- [Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting](https://mlsanity.com/paper/2310.10642/) (2023)
- [LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS](https://mlsanity.com/paper/2311.17245/) (2023)
- [Single Path One-Shot Neural Architecture Search with Uniform Sampling](https://mlsanity.com/paper/1904.00420/) (2019)
- [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)
- [HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks](https://mlsanity.com/paper/1911.03852/) (2019)
- [Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussians](https://mlsanity.com/paper/2403.17898/) (2024)
- [Mini-Splatting: Representing Scenes with a Constrained Number of Gaussians](https://mlsanity.com/paper/2403.14166/) (2024)
- [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)
- [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)
- [CompGS: Smaller and Faster Gaussian Splatting with Vector Quantization](https://mlsanity.com/paper/2311.18159/) (2023)
- [Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats](https://mlsanity.com/paper/2410.12781/) (2024)
- [ContextGS: Compact 3D Gaussian Splatting with Anchor Level Context Model](https://mlsanity.com/paper/2405.20721/) (2024)
- [Practical Full Resolution Learned Lossless Image Compression](https://mlsanity.com/paper/1811.12817/) (2018)
- [CompGS: Efficient 3D Scene Representation via Compressed Gaussian Splatting](https://mlsanity.com/paper/2404.09458/) (2024)
- [End-to-End Rate-Distortion Optimized 3D Gaussian Representation](https://mlsanity.com/paper/2406.01597/) (2024)
- [3DGS.zip: A survey on 3D Gaussian Splatting Compression Methods](https://mlsanity.com/paper/2407.09510/) (2024)
- [MesonGS: Post-training Compression of 3D Gaussians via Efficient Attribute Transformation](https://mlsanity.com/paper/2409.09756/) (2024)
- [LaRa: Efficient Large-Baseline Radiance Fields](https://mlsanity.com/paper/2407.04699/) (2024)
- [Trimming the Fat: Efficient Compression of 3D Gaussian Splats through Pruning](https://mlsanity.com/paper/2406.18214/) (2024)
- [Spectrally Pruned Gaussian Fields with Neural Compensation](https://mlsanity.com/paper/2405.00676/) (2024)
- [HEMGS: A Hybrid Entropy Model for 3D Gaussian Splatting Data Compression](https://mlsanity.com/paper/2411.18473/) (2024)
- [Implicit Gaussian Splatting with Efficient Multi-Level Tri-Plane Representation](https://mlsanity.com/paper/2408.10041/) (2024)
- [NeRFCodec: Neural Feature Compression Meets Neural Radiance Fields for Memory-Efficient Scene Representation](https://mlsanity.com/paper/2404.02185/) (2024)

## Built on by (most cited first, 7 of 7)

- [PCGS: Progressive Compression of 3D Gaussian Splatting](https://mlsanity.com/paper/2503.08511/) (2025)
- [SD-GS: Structured Deformable 3D Gaussians for Efficient Dynamic Scene Reconstruction](https://mlsanity.com/paper/2507.07465/) (2025)
- [Tail-Aware Post-Training Quantization for 3D Geometry Models](https://mlsanity.com/paper/2602.01741/) (2026)
- [Learning Hierarchical Sparse Transform Coding for 3DGS Compression](https://mlsanity.com/paper/2505.22908/) (2025)
- [Transforming harmonic coefficients for 3D splat compression](https://mlsanity.com/paper/2609.15735/) (2026)
- [MesonGS++: Post-training Compression of 3D Gaussian Splatting with Hyperparameter Searching](https://mlsanity.com/paper/2604.26799/) (2026)
- [CAGS: Color-Adaptive Volumetric Video Streaming with Dynamic 3D Gaussian Splatting](https://mlsanity.com/paper/2605.09279/) (2026)

## Abstract (arXiv)

Recent advances in 3D Gaussian Splatting (3DGS) have greatly improved 3D reconstruction. However, its substantial data size poses a significant challenge for transmission and storage. While many compression techniques have been proposed, they fail to efficiently adapt to fluctuating network bandwidth, leading to resource wastage. We address this issue from the perspective of size-aware compression, where we aim to compress 3DGS to a desired size by quickly searching for suitable hyperparameters. Through a measurement study, we identify key hyperparameters that affect the size -- namely, the reserve ratio of Gaussians and bit-width settings for Gaussian attributes. Then, we formulate this hyperparameter optimization problem as a mixed-integer nonlinear programming (MINLP) problem, with the goal of maximizing visual quality while respecting the size budget constraint. To solve the MINLP, we decouple this problem into two parts: discretely sampling the reserve ratio and determining the bit-width settings using integer linear programming (ILP). To solve the ILP more quickly and accurately, we design a quality loss estimator and a calibrated size estimator, as well as implement a CUDA kernel. Extensive experiments on multiple 3DGS variants demonstrate that our method achieves state-of-the-art performance in post-training compression. Furthermore, our method can achieve comparable quality to leading training-required methods after fine-tuning.