Efficient Perspective-Correct 3D Gaussian Splatting Using Hybrid Transparency

Abstract

3D Gaussian Splats (3DGS) have proven a versatile rendering primitive, both for inverse rendering as well as real-time exploration of scenes. In these applications, coherence across camera frames and multiple views is crucial, be it for robust convergence of a scene reconstruction or for artifact-free fly-throughs. Recent work started mitigating artifacts that break multi-view coherence, including popping artifacts due to inconsistent transparency sorting and perspective-correct outlines of (2D) splats. At the same time, real-time requirements forced such implementations to accept compromises in how transparency of large assemblies of 3D Gaussians is resolved, in turn breaking coherence in other ways. In our work, we aim at achieving maximum coherence, by rendering fully perspective-correct 3D Gaussians while using a high-quality approximation of accurate blending, hybrid transparency, on a per-pixel level, in order to retain real-time frame rates. Our fast and perspectively accurate approach for evaluation of 3D Gaussians does not require matrix inversions, thereby ensuring numerical stability and eliminating the need for special handling of degenerate splats, and the hybrid transparency formulation for blending maintains similar quality as fully resolved per-pixel transparencies at a fraction of the rendering costs. We further show that each of these two components can be independently integrated into Gaussian splatting systems. In combination, they achieve up to 2× higher frame rates, 2× faster optimization, and equal or better image quality with fewer rendering artifacts compared to traditional 3DGS on common benchmarks.

Citation Style:    Display Alpha ACM SIGGRAPH IEEEtran Publication

Efficient Perspective-Correct 3D Gaussian Splatting Using Hybrid Transparency. Florian Hahlbohm, Fabian Friederichs, Tim Weyrich, Linus Franke, Moritz Kappel, Susana Castillo, Marc Stamminger, Martin Eisemann, Marcus Magnor. Conditionally accepted, Computer Graphics Forum (Proc. Eurographics), 44(2), 12 pages, 2025.Florian Hahlbohm, Fabian Friederichs, Tim Weyrich, Linus Franke, Moritz Kappel, Susana Castillo, Marc Stamminger, Martin Eisemann, and Marcus Magnor. Efficient perspective-correct 3D gaussian splatting using hybrid transparency. Computer Graphics Forum (Proc. Eurographics), 44(2), May 2025.Hahlbohm, F., Friederichs, F., Weyrich, T., Franke, L., Kappel, M., Castillo, S., Stamminger, M., Eisemann, M., and Magnor, M. 2025. Efficient perspective-correct 3D gaussian splatting using hybrid transparency. Computer Graphics Forum (Proc. Eurographics) 44, 2 (May).F. Hahlbohm, F. Friederichs, T. Weyrich, L. Franke, M. Kappel, S. Castillo, M. Stamminger, M. Eisemann, and M. Magnor, “Efficient perspective-correct 3D gaussian splatting using hybrid transparency,” Computer Graphics Forum (Proc. Eurographics), vol. 44, no. 2, May 2025. PDF (25 MB) Low-res PDF (4.9 MB) BibTeX GitHub Project Page

Related Publications

A Hardware Architecture for Surface Splatting. Tim Weyrich, Simon Heinzle, Timo Aila, Daniel B. Fasnacht, Stephan Oetiker, Mario Botsch, Cyril Flaig, Simon Mall, Kaspar Rohrer, Norbert Felber, Hubert Kaeslin, Markus Gross. In ACM Transactions on Graphics (Proc. SIGGRAPH), 26, 3 (Jul. 2007), 90:1–90:11, Los Angeles, CA, 2007.Tim Weyrich, Simon Heinzle, Timo Aila, Daniel Fasnacht, Stephan Oetiker, Mario Botsch, Cyril Flaig, Simon Mall, Kaspar Rohrer, Norbert Felber, Hubert Kaeslin, and Markus Gross. A hardware architecture for surface splatting. ACM Trans. on Graphics (Proc. SIGGRAPH 2007), 26(3):90:1–90:11, 2007.Weyrich, T., Heinzle, S., Aila, T., Fasnacht, D., Oetiker, S., Botsch, M., Flaig, C., Mall, S., Rohrer, K., Felber, N., Kaeslin, H., and Gross, M. 2007. A hardware architecture for surface splatting.ACM Trans. on Graphics (Proc. SIGGRAPH 2007) 26, 3, 90:1–90:11.T. Weyrich, S. Heinzle, T. Aila, D. Fasnacht, S. Oetiker, M. Botsch, C. Flaig, S. Mall, K. Rohrer, N. Felber, H. Kaeslin, and M. Gross, “A hardware architecture for surface splatting,” ACM Trans. on Graphics (Proc. SIGGRAPH 2007), vol. 26, no. 3, pp. 90:1–90:11, 2007. [Web Page][PDF][Video][BibTeX][DOI]

GPU-Based Ray Casting of Quadratic Surfaces. Christian Sigg, Tim Weyrich, Mario Botsch, Markus Gross. In Proceedings of Eurographics Symposium on Point-Based Graphics, July 29-30, 2006, Boston.Christian Sigg, Tim Weyrich, Mario Botsch, and Markus Gross. GPU-based ray-casting of quadratic surfaces. In Proceedings of 3rd Eurographics Symposium on Point-Based Graphics, pages 59–65. Eurographics Association, July 2006.Sigg, C., Weyrich, T., Botsch, M., and Gross, M. 2006. GPU-based ray-casting of quadratic surfaces. In Proceedings of 3rd Eurographics Symposium on Point-Based Graphics, Eurographics Association, 59–65.C. Sigg, T. Weyrich, M. Botsch, and M. Gross, “GPU-based ray-casting of quadratic surfaces,” in Proceedings of 3rd Eurographics Symposium on Point-Based Graphics. Eurographics Association, Jul. 2006, pp. 59–65. [Web Page][PDF][Video][Errata][BibTeX]

Acknowledgments

We would like to thank Timon Scholz and Carlotta Harms for their help with comparisons and the supplemental material. The authors gratefully acknowledge financial support from the German Research Foundation (DFG) for the projects “Real-Action VR” (ID 523421583) and “Increasing Realism of Omnidirectional Videos in Virtual Reality” (ID 491805996), as well as from the L3S Research Center, Hanover, Germany. Linus Franke was supported by the 5G innovation program of the German Federal Ministry for Digital and Transport under the funding code 165GU103B.