Smaller and Faster 3DGS via Post-Training Dictionary Learning
This work provides a practical solution for deploying 3DGS models on less powerful devices by significantly reducing their memory footprint and improving rendering performance, which is beneficial for real-time applications.
This paper addresses the large memory footprint of 3D Gaussian Splatting (3DGS) models, which hinders their deployment on resource-constrained devices. The authors introduce a post-training dictionary-learning-based compression framework that achieves average compression ratios of 3.95x for 3DGS, 3.10x for 3DGS-MCMC, and 4.55x for PixelGS, resulting in rendering speedups of 23.3%, 24.3%, and 25.3% respectively, all while preserving image quality.
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.