Generalized non-exponential Gaussian splatting

2026-03-03

AI Summary

This work addresses the severe overdraw and rendering inefficiency in traditional 3D Gaussian Splatting (3DGS) caused by its exponential attenuation-based transmittance model, particularly in complex scenes. To overcome this limitation, the study introduces non-exponential radiative transfer theory into the 3DGS framework for the first time, proposing sublinear, linear, and superlinear image formation models based on a quadratic transmittance function. Corresponding non-exponential alpha blending operators and a tailored ray tracing rendering pipeline are designed to support these models. The proposed method achieves comparable reconstruction quality to the original 3DGS while significantly reducing overdraw, yielding up to a 4× rendering speedup in real-world complex scenes.

Technology Category

• Computer Vision: 3D Computer Vision
• Search and Optimization: Non-convex Optimization
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Security and Privacy: Data transparency and provenance
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

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.

Problem

• 3D Gaussian splatting
• non-exponential radiative transfer
• alpha-blending
• overdraw reduction
• rendering efficiency

Innovation

• non-exponential radiative transfer
• 3D Gaussian splatting
• alpha-blending generalization
• quadratic transmittance
• overdraw reduction