Generalized non-exponential Gaussian splatting

TL;DR

This paper extends 3D Gaussian splatting to non-exponential radiative transfer models, enabling faster rendering with similar quality by reducing overdraws in complex scenes.

Contribution

It introduces non-exponential variants of 3DGS using quadratic transmittance, broadening the model's applicability and improving rendering efficiency.

Findings

Achieves up to 4x speed-up in complex scenes

Maintains similar rendering quality to original 3DGS

Reduces overdraws significantly

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 $4\times$ in complex real-world captures, on a ray-tracing-based renderer.