Improving Adaptive Density Control for 3D Gaussian Splatting

Glenn Grubert, Glenn Grubert, Florian Barthel, Florian Barthel, Anna Hilsmann, Peter Eisert, Peter Eisert

2025

Abstract

3D Gaussian Splatting (3DGS) has become one of the most influential works in the past year. Due to its efficient and high-quality novel view synthesis capabilities, it has been widely adopted in many research fields and applications. Nevertheless, 3DGS still faces challenges to properly manage the number of Gaussian primitives that are used during scene reconstruction. Following the adaptive density control (ADC) mechanism of 3D Gaussian Splatting, new Gaussians in under-reconstructed regions are created, while Gaussians that do not contribute to the rendering quality are pruned. We observe that those criteria for densifying and pruning Gaussians can sometimes lead to worse rendering by introducing artifacts. We especially observe under-reconstructed background or overfitted foreground regions. To encounter both problems, we propose three new improvements to the adaptive density control mechanism. Those include a correction for the scene extent calculation that does not only rely on camera positions, an exponentially ascending gradient threshold to improve training convergence, and significance-aware pruning strategy to avoid background artifacts. With these adaptions, we show that the rendering quality improves while using the same number of Gaussians primitives. Furthermore, with our improvements, the training converges considerably faster, allowing for more than twice as fast training times while yielding better quality than 3DGS. Finally, our contributions are easily compatible with most existing derivative works of 3DGS making them relevant for future works.

Paper Citation

in Harvard Style

Grubert G., Barthel F., Hilsmann A. and Eisert P. (2025). Improving Adaptive Density Control for 3D Gaussian Splatting. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-728-3, SciTePress, pages 610-621. DOI: 10.5220/0013308500003912

in Bibtex Style

@conference{visapp25,
author={Glenn Grubert and Florian Barthel and Anna Hilsmann and Peter Eisert},
title={Improving Adaptive Density Control for 3D Gaussian Splatting},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2025},
pages={610-621},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013308500003912},
isbn={978-989-758-728-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - Improving Adaptive Density Control for 3D Gaussian Splatting
SN - 978-989-758-728-3
AU - Grubert G.
AU - Barthel F.
AU - Hilsmann A.
AU - Eisert P.
PY - 2025
SP - 610
EP - 621
DO - 10.5220/0013308500003912
PB - SciTePress