# Trimming the Fat: Efficient Compression of 3D Gaussian Splats through Pruning arXiv: https://arxiv.org/abs/2406.18214 · HTML: https://mlsanity.com/paper/2406.18214/ ## Key facts - Cited by 47 papers in the map (data through 14 Oct 2026). - Builds on 24 of its 33 references that are in the map. - First posted on arXiv 26 Jun 2024. ## Builds on (most cited first, 24 of 24) - [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) - [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018) - [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) - [pixelNeRF: Neural Radiance Fields from One or Few Images](https://mlsanity.com/paper/2012.02190/) (2020) - [Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction](https://mlsanity.com/paper/2111.11215/) (2021) - [K-Planes: Explicit Radiance Fields in Space, Time, and Appearance](https://mlsanity.com/paper/2301.10241/) (2023) - [Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering](https://mlsanity.com/paper/2312.00109/) (2023) - [What is the State of Neural Network Pruning?](https://mlsanity.com/paper/2003.03033/) (2020) - [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) - [DeepVoxels: Learning Persistent 3D Feature Embeddings](https://mlsanity.com/paper/1812.01024/) (2018) - [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) - [Kernel and Rich Regimes in Overparametrized Models](https://mlsanity.com/paper/2002.09277/) (2020) - [Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesis](https://mlsanity.com/paper/2401.02436/) (2023) - [Free View Synthesis](https://mlsanity.com/paper/2008.05511/) (2020) - [HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compression](https://mlsanity.com/paper/2403.14530/) (2024) - [DeepStereo: Learning to Predict New Views from the World's Imagery](https://mlsanity.com/paper/1506.06825/) (2015) - [Escaping Plato's Cave: 3D Shape From Adversarial Rendering](https://mlsanity.com/paper/1811.11606/) (2018) - [StylizedNeRF: Consistent 3D Scene Stylization as Stylized NeRF via 2D-3D Mutual Learning](https://mlsanity.com/paper/2205.12183/) (2022) - [Compressing Explicit Voxel Grid Representations: fast NeRFs become also small](https://mlsanity.com/paper/2210.12782/) (2022) - [Neural Radiance Fields Approach to Deep Multi-View Photometric Stereo](https://mlsanity.com/paper/2110.05594/) (2021) ## Built on by (most cited first, 30 of 47) - [Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives](https://mlsanity.com/paper/2412.00578/) (2024) - [HAC++: Towards 100X Compression of 3D Gaussian Splatting](https://mlsanity.com/paper/2501.12255/) (2025) - [Fast Feedforward 3D Gaussian Splatting Compression](https://mlsanity.com/paper/2410.08017/) (2024) - [FastGS: Training 3D Gaussian Splatting in 100 Seconds](https://mlsanity.com/paper/2511.04283/) (2025) - [CAT-3DGS: A Context-Adaptive Triplane Approach to Rate-Distortion-Optimized 3DGS Compression](https://mlsanity.com/paper/2503.00357/) (2025) - [Compression of 3D Gaussian Splatting with Optimized Feature Planes and Standard Video Codecs](https://mlsanity.com/paper/2501.03399/) (2025) - [PCGS: Progressive Compression of 3D Gaussian Splatting](https://mlsanity.com/paper/2503.08511/) (2025) - [Efficient Scene Modeling via Structure-Aware and Region-Prioritized 3D Gaussians](https://mlsanity.com/paper/2411.12788/) (2024) - [NeRF Is a Valuable Assistant for 3D Gaussian Splatting](https://mlsanity.com/paper/2507.23374/) (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) - [GoDe: Gaussians on Demand for Progressive Level of Detail and Scalable Compression](https://mlsanity.com/paper/2501.13558/) (2025) - [FlexGaussian: Flexible and Cost-Effective Training-Free Compression for 3D Gaussian Splatting](https://mlsanity.com/paper/2507.06671/) (2025) - [Gaussian Herding across Pens: An Optimal Transport Perspective on Global Gaussian Reduction for 3DGS](https://mlsanity.com/paper/2506.09534/) (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) - [EntropyGS: An Efficient Entropy Coding on 3D Gaussian Splatting](https://mlsanity.com/paper/2508.10227/) (2025) - [Feed-Forward 3D Gaussian Splatting Compression with Long-Context Modeling](https://mlsanity.com/paper/2512.00877/) (2025) - [SpeeDe3DGS: Speedy Deformable 3D Gaussian Splatting with Temporal Pruning and Motion Grouping](https://mlsanity.com/paper/2506.07917/) (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) - [REFINE: Super-efficient 3D Gaussian Splatting Pruning via Rendering-Free Primitive Importance](https://mlsanity.com/paper/2606.09074/) (2026) - [Trick-GS: A Balanced Bag of Tricks for Efficient Gaussian Splatting](https://mlsanity.com/paper/2501.14534/) (2025) - [ControlGS: Consistent Structural Compression Control for Deployment-Aware Gaussian Splatting](https://mlsanity.com/paper/2505.10473/) (2025) - [SUCCESS-GS: Survey of Compactness and Compression for Efficient Static and Dynamic Gaussian Splatting](https://mlsanity.com/paper/2512.07197/) (2025) - [Splatwizard: A Benchmark Toolkit for 3D Gaussian Splatting Compression](https://mlsanity.com/paper/2512.24742/) (2025) - [PackUV: Packed Gaussian UV Maps for 4D Volumetric Video](https://mlsanity.com/paper/2602.23040/) (2026) - [CodecSplat: Ultra-Compact Latent Coding for Feed-Forward 3D Gaussian Splatting](https://mlsanity.com/paper/2605.25563/) (2026) - [Provable Pruning for Efficient 3D Gaussian Splatting via Coresets](https://mlsanity.com/paper/2607.02721/) (2026) - [SPARE-GS: Structural Parsimony and Resource Efficiency for 3D Gaussian Splatting](https://mlsanity.com/paper/2607.16624/) (2026) ## Abstract (arXiv) In recent times, the utilization of 3D models has gained traction, owing to the capacity for end-to-end training initially offered by Neural Radiance Fields and more recently by 3D Gaussian Splatting (3DGS) models. The latter holds a significant advantage by inherently easing rapid convergence during training and offering extensive editability. However, despite rapid advancements, the literature still lives in its infancy regarding the scalability of these models. In this study, we take some initial steps in addressing this gap, showing an approach that enables both the memory and computational scalability of such models. Specifically, we propose "Trimming the fat", a post-hoc gradient-informed iterative pruning technique to eliminate redundant information encoded in the model. Our experimental findings on widely acknowledged benchmarks attest to the effectiveness of our approach, revealing that up to 75% of the Gaussians can be removed while maintaining or even improving upon baseline performance. Our approach achieves around 50× compression while preserving performance similar to the baseline model, and is able to speed-up computation up to 600 FPS.