Smaller and Faster 3DGS via Post-Training Dictionary Learning

• URL: http://arxiv.org/abs/2605.30396v1
• Date: Thu, 28 May 2026 14:14:40 GMT
• Title: Smaller and Faster 3DGS via Post-Training Dictionary Learning
• Abstract summary: We introduce the first dictionary-learning-based compression framework for 3DGS.<n>Our approach achieves an average compression ratio of 3.95x, 3.10x, and 4.55x when applied to 3DGS, 3DGS-MCMC, and PixelGS.<n>This yields consistent rendering speedups of 23.3%, 24.3%, and 25.3%, while maintaining image quality.
• Score: 2.1839191255085995
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 3D Gaussian Splatting (3DGS) is a promising neural scene representation for real-time rendering, but trained models often suffer from large memory footprints, limiting deployment on less powerful devices. Existing compression techniques often lead to architectures with several additional trainable parameters. While achieving outstanding compression ratios, they introduce noticeable drops in image quality. In this work, we introduce the first dictionary-learning-based compression framework for 3DGS. The proposed post-training compression pipeline can be deployed in virtually any 3DGS model without the need for re-training or modifications to existing 3DGS models. Our compression framework is straightforward to implement, yet provides significant compression capabilities, preserves image quality, and improves real-time rendering performance. Across 13 benchmark scenes, our approach achieves an average compression ratio of 3.95x, 3.10x, and 4.55x when applied to 3DGS, 3DGS-MCMC, and PixelGS, respectively. This yields consistent rendering speedups of 23.3%, 24.3%, and 25.3%, while maintaining image quality.

Related papers

• Splatwizard: A Benchmark Toolkit for 3D Gaussian Splatting Compression [69.94586602640355]
  We introduce Splatwizard, a unified benchmark toolkit designed specifically for 3DGS compression models.<n>Splatwizard provides an easy-to-use framework to implement new 3DGS compression model and utilize state-of-the-art techniques.
  arXiv  Detail & Related papers  (2025-12-31T09:26:04Z)
• RAVE: Rate-Adaptive Visual Encoding for 3D Gaussian Splatting [17.19039932786604]
  We propose a flexible compression scheme for 3DGS that supports at any rate between predefined bounds.<n>Our method is computationally lightweight, requires no retraining for any rate, and preserves rendering quality across a broad range of operating points.<n> Experiments demonstrate that the approach achieves efficient, high-quality compression while offering dynamic rate control, making it suitable for practical deployment in immersive applications.
  arXiv  Detail & Related papers  (2025-12-07T23:59:46Z)
• Leveraging Learned Image Prior for 3D Gaussian Compression [47.29061692878941]
  We introduce a novel 3DGS compression framework that leverages the powerful representational capacity of learned image priors to recover compression-induced quality degradation.<n>Our framework is designed to be compatible with existing Gaussian compression methods, making it broadly applicable across different baselines.
  arXiv  Detail & Related papers  (2025-10-16T14:10:02Z)
• ExGS: Extreme 3D Gaussian Compression with Diffusion Priors [60.7245825868903]
  We introduce ExGS and GaussPainter for Extreme 3DGS compression.<n>GassPainter fills in missing regions and enhances visible pixels, yielding substantial improvements in degraded renderings.<n>Our framework can even achieve over 100X compression (reducing a typical 354.77 MB model to about 3.31 MB)
  arXiv  Detail & Related papers  (2025-09-29T13:23:06Z)
• Compressing 3D Gaussian Splatting by Noise-Substituted Vector Quantization [14.71160140310766]
  3D Gaussian Splatting (3DGS) has demonstrated remarkable effectiveness in 3D reconstruction, achieving high-quality results with real-time radiance field rendering.<n>However, a key challenge is the substantial storage cost: reconstructing a single scene typically requires millions of Gaussian splats, each represented by 59 floating-point parameters, resulting in approximately 1 GB of memory.<n>We propose a compression method by building separate attribute codebooks and storing only discrete code indices. Specifically, we employ noise-substituted vector quantization technique to jointly train the codebooks and model features, ensuring consistency between descent gradient optimization and parameter discretization
  arXiv  Detail & Related papers  (2025-04-03T22:19:34Z)
• Fast Feedforward 3D Gaussian Splatting Compression [55.149325473447384]
  3D Gaussian Splatting (FCGS) is an optimization-free model that can compress 3DGS representations rapidly in a single feed-forward pass.<n>FCGS achieves a compression ratio of over 20X while maintaining fidelity, surpassing most per-scene SOTA optimization-based methods.
  arXiv  Detail & Related papers  (2024-10-10T15:13:08Z)
• Compact 3D Gaussian Splatting for Static and Dynamic Radiance Fields [13.729716867839509]
  We propose a learnable mask strategy that significantly reduces the number of Gaussians while preserving high performance. In addition, we propose a compact but effective representation of view-dependent color by employing a grid-based neural field. Our work provides a comprehensive framework for 3D scene representation, achieving high performance, fast training, compactness, and real-time rendering.
  arXiv  Detail & Related papers  (2024-08-07T14:56:34Z)
• PUP 3D-GS: Principled Uncertainty Pruning for 3D Gaussian Splatting [59.277480452459315]
  We propose a principled sensitivity pruning score that preserves visual fidelity and foreground details at significantly higher compression ratios.<n>We also propose a multi-round prune-refine pipeline that can be applied to any pretrained 3D-GS model without changing its training pipeline.
  arXiv  Detail & Related papers  (2024-06-14T17:53:55Z)
• ContextGS: Compact 3D Gaussian Splatting with Anchor Level Context Model [77.71796503321632]
  We introduce a context model in the anchor level for 3DGS representation, yielding an impressive size reduction of over 100 times compared to vanilla 3DGS. Our work pioneers the context model in the anchor level for 3DGS representation, yielding an impressive size reduction of over 100 times compared to vanilla 3DGS and 15 times compared to the most recent state-of-the-art work Scaffold-GS.
  arXiv  Detail & Related papers  (2024-05-31T09:23:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.