Abstract

---

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.

Citation

---

@misc{hahlbohm2026fastergs,
  title         = {Faster-GS: Analyzing and Improving Gaussian Splatting Optimization},
  author        = {Florian Hahlbohm and Linus Franke and Martin Eisemann and Marcus Magnor},
  year          = {2026},
  eprint        = {2602.xxxxx},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CV},
  url           = {https://arxiv.org/abs/2602.xxxxx},
}

Acknowledgements

---

This work was partially funded by the DFG projects “Real-Action VR” (ID 523421583) and “Increasing Realism of Omnidirectional Videos in Virtual Reality” (ID 491805996). Linus Franke was supported by the ERC Advanced Grant NERPHYS (ID 101141721).

The website template was adapted from Zip-NeRF, who borrowed from Michaël Gharbi and Ref-NeRF.