English

Generalized non-exponential Gaussian splatting

Graphics 2026-03-05 v2 Computer Vision and Pattern Recognition

Abstract

In this work we generalize 3D Gaussian splatting (3DGS) to a wider family of physically-based alpha-blending operators. 3DGS has become the standard de-facto for radiance field rendering and reconstruction, given its flexibility and efficiency. At its core, it is based on alpha-blending sorted semitransparent primitives, which in the limit converges to the classic radiative transfer function with exponential transmittance. Inspired by recent research on non-exponential radiative transfer, we generalize the image formation model of 3DGS to non-exponential regimes. Based on this generalization, we use a quadratic transmittance to define sub-linear, linear, and super-linear versions of 3DGS, which exhibit faster-than-exponential decay. We demonstrate that these new non-exponential variants achieve similar quality than the original 3DGS but significantly reduce the number of overdraws, which result on speed-ups of up to 4×4\times in complex real-world captures, on a ray-tracing-based renderer.

Keywords

Cite

@article{arxiv.2603.02887,
  title  = {Generalized non-exponential Gaussian splatting},
  author = {Sébastien Speierer and Adrian Jarabo},
  journal= {arXiv preprint arXiv:2603.02887},
  year   = {2026}
}

Comments

13 pages, 6 figures, 4 tables

R2 v1 2026-07-01T11:00:51.904Z