Computer Graphics
TU Braunschweig

Faster-GS: Analyzing and Improving Gaussian Splatting Optimization


Faster-GS: Analyzing and Improving Gaussian Splatting Optimization

Recent advances in 3D Gaussian Splatting (3DGS) have focused on accelerating optimization while preserving reconstruction quality. However, many proposed methods entangle implementation-level improvements with fundamental algorithmic modifications or trade performance for fidelity, leading to a fragmented research landscape that complicates fair comparison.

In this work, we consolidate and evaluate the most effective and broadly applicable strategies from prior 3DGS research and augment them with several novel optimizations. We further investigate underexplored aspects of the framework, including numerical stability, Gaussian truncation, and gradient approximation. The resulting system, Faster-GS, provides a rigorously optimized algorithm that we evaluate across a comprehensive suite of benchmarks.

Our experiments demonstrate that Faster-GS achieves up to 5× faster training while maintaining visual quality, establishing a new cost-effective and resource efficient baseline for 3DGS optimization. Furthermore, we demonstrate that optimizations can be applied to 4D Gaussian reconstruction, leading to efficient non-rigid scene optimization.


Author(s): Florian Hahlbohm, Linus Franke, Martin Eisemann, Marcus Magnor
Published: to appear
Type: Article in conference proceedings
Book: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Presented at: Conference on Computer Vision and Pattern Recognition (CVPR) 2026
Project(s): Real-Action VR  Increasing Realism of Omnidirectional Videos in Virtual Reality 


@inproceedings{hahlbohm2026faster-gs,
  title = {Faster-{GS}: Analyzing and Improving Gaussian Splatting Optimization},
  author = {Hahlbohm, Florian and Franke, Linus and Eisemann, Martin and Magnor, Marcus},
  booktitle = {{IEEE}/{CVF} Conference on Computer Vision and Pattern Recognition ({CVPR})},
  year = {2026}
}

Authors