GSta: Efficient Training Scheme with Siestaed Gaussians for Monocular 3D Scene Reconstruction
In Submission

Anil Armagan1, Albert Saá Garriga1, Bruno Manganelli1, Kyuwon Kim2, M. Kerim Yucel1

1Samsung R&D Institute UK (SRUK), 2Samsung Electronics


Paper
--> Code (coming soon)


Supplementary video of our method.


3DGS Taming-3DGS Mini-Splatting2 GSta-TrickGS-small

Qualitative comparison with example from MipNeRF-360 - bicycle scene.


3DGS Taming-3DGS Mini-Splatting2 GSta-TrickGS-small

Qualitative comparison with example image from MipNeRF-360 - bicycle scene.

BibTeX

      
        @Article{armagan2025gsta,
      author       = {Armagan},
      title        = {GSta: Efficient Training Scheme with Siestaed Gaussians for Monocular 3D Scene Reconstruction},
      journal      = {arXiv preprint arXiv:2504.06716},
      year         = {2025},
      url          = {https://github.com/anilarmagan/SRUK-GSta)}
}

References

[Kerbl 2023] Kerbl et al. 3D Gaussian Splatting for Real-Time Radiance Field Rendering. ACM Transactions on Graphics (ToG), 42(4).

[Taming 3DGS 2024] Mallick et al. Taming 3DGS: High-Quality Radiance Fields with Limited Resources. SIGGRAPH Asia. 2024

[Mini-Splatting2] Guangchi Fang and Bing Wang. Mini-Splatting2: Building 360 Scenes within Minutes via Aggressive Gaussian Densification. arXiv preprint arXiv:2411.12788. 2024.

[Trick-GS 2025] Armagan et al. Trick-GS: A Balanced Bag of Tricks for Efficient Gaussian Splatting. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2025.

[Hedman 2018] Hedman et al. Deep blending for free-viewpoint image-based rendering. ACM Transactions on Graphics (ToG), 37(6), pp.1-15. 2018.

[Barron 2022] Barron, Jonathan T., et al. "Mip-NeRF 360: Unbounded anti-aliased neural radiance fields." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2022.

[Knapitsch 2017] Knapitsch, Arno, et al. "Tanks and temples: Benchmarking large-scale scene reconstruction." ACM Transactions on Graphics (ToG) 36.4. 2017.