Stochastic ray tracing of 3D transparent Gaussians

Xin Sun, Iliyan Georgiev, Yun Fei, Miloš Hašan
Arxiv 2025

Left: A seashell ray-traced with our method, in a scene made with traditional meshes and physically based materials. The asset is reconstructed using 3D Gaussian splatting from a phone-captured video. Shadows, glossy reflections on the base, refractions in curved glass, and depth-of-field effects are seamlessly added using a Monte Carlo path tracer integrating our method. Right: We mix assets made of meshes and complex materials within a Gaussian splatting scene asset.

Abstract

3D Gaussian splatting has recently been widely adopted as a 3D representation for novel-view synthesis, relighting, and text-to-3D generation tasks, offering realistic and detailed results through a collection of explicit 3D Gaussians carrying opacities and view-dependent colors. However, efficient rendering of many transparent primitives remains a significant challenge. Existing approaches either rasterize the 3D Gaussians with approximate sorting per view or rely on high-end RTX GPUs to exhaustively process all ray-Gaussian intersections (bounding Gaussians by meshes). This paper proposes a stochastic ray tracing method to render 3D clouds of transparent primitives. Instead of processing all ray-Gaussian intersections in sequential order, each ray traverses the acceleration structure only once, randomly accepting and shading a single intersection (or N intersections, using a simple extension). This approach minimizes shading time and avoids sorting the Gaussians along the ray while minimizing the register usage and maximizing parallelism even on low-end GPUs. The cost of rays through the Gaussian asset is comparable to that of standard mesh-intersection rays. While our method introduces noise, the shading is unbiased, and the variance is slight, as stochastic acceptance is importance-sampled based on accumulated opacity. The alignment with the Monte Carlo philosophy simplifies implementation and easily integrates our method into a conventional path-tracing framework.

Downloads and links

BibTeX reference

@misc{Sun:2025:GaussianRayTracing,
    title={Stochastic Ray Tracing of 3D Transparent Gaussians},
    author={Xin Sun and Iliyan Georgiev and Yun Fei and Miloš Hašan},
    year={2025},
    eprint={2504.06598},
    archivePrefix={arXiv},
    primaryClass={cs.GR},
    url={https://arxiv.org/abs/2504.06598}
}