Temporally Compressed 3D Gaussian Splatting for Dynamic Scenes


Saqib Javed (CVLab, EPFL), Ahmad Jarrar Khan (CVLab, EPFL), Corentin Dumery (CVLab, EPFL), Chen Zhao (CVLab, EPFL), Mathieu Salzmann (CVLab, EPFL, Swiss Data Science Center)
The 35th British Machine Vision Conference
PDFPosterVideo (Right click to download)Supplementary

Abstract

Recent advancements in high-fidelity dynamic scene reconstruction have leveraged dynamic 3D Gaussians and 4D Gaussian Splatting for realistic scene representation. However, to make these methods viable for real-time applications such as AR/VR, gaming, and rendering on low-power devices, substantial reductions in memory usage and improvements in rendering efficiency are required. While many state-of-the-art methods prioritize lightweight implementations, they struggle in handling scenes with complex motions or long sequences. In this work, we introduce Temporally Compressed 3D Gaussian Splatting (TC3DGS), a novel technique designed specifically to effectively compress dynamic 3D Gaussian representations. TC3DGS selectively prunes Gaussians based on their temporal relevance and employs gradient-aware mixed-precision quantization to dynamically compress Gaussian parameters. In addition, TC3DGS exploits an adapted version of the Ramer-Douglas-Peucker algorithm to further reduce storage by interpolating Gaussian trajectories across frames. Our experiments on multiple datasets demonstrate that TC3DGS achieves up to 67$\times$ compression with minimal or no degradation in visual quality. Project Page: https://ahmad-jarrar.github.io/tc-3dgs/

Citation

@inproceedings{Javed_2025_BMVC,
author    = {Saqib Javed and Ahmad Jarrar Khan and Corentin Dumery and Chen Zhao and Mathieu Salzmann},
title     = {Temporally Compressed 3D Gaussian Splatting for Dynamic Scenes},
booktitle = {36th British Machine Vision Conference 2025, {BMVC} 2025, Sheffield, UK, November 24-27, 2025},
publisher = {BMVA},
year      = {2025},
url       = {https://bmva-archive.org.uk/bmvc/2025/assets/papers/Paper_543/paper.pdf}
}


Copyright © 2025 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection