Stochastic Ray Tracing of Transparent 3D Gaussians

dc.contributor.authorSun, Xinen_US
dc.contributor.authorGeorgiev, Iliyanen_US
dc.contributor.authorFei, Yun (Raymond)en_US
dc.contributor.authorHasan, Milosen_US
dc.contributor.editorWang, Beibeien_US
dc.contributor.editorWilkie, Alexanderen_US
dc.date.accessioned2025-06-20T07:49:44Z
dc.date.available2025-06-20T07:49:44Z
dc.date.issued2025
dc.description.abstract3D Gaussian splatting has been widely adopted as a 3D representation for novel-view synthesis, relighting, and 3D generation tasks. It delivers realistic and detailed results through a collection of explicit 3D Gaussian primitives, each carrying opacity and view-dependent color. However, efficient rendering of many transparent primitives remains a significant challenge. Existing approaches either rasterize the Gaussians with approximate per-view sorting or rely on high-end RTX GPUs. 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 primitive sorting along the ray, thereby minimizing 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. The shading is unbiased and has low variance, as our stochastic acceptance achieves importance sampling based on accumulated weight. The alignment with Monte Carlo philosophy simplifies implementation and integration into a conventional path-tracing framework.en_US
dc.description.sectionheadersGaussians
dc.description.seriesinformationEurographics Symposium on Rendering
dc.identifier.doi10.2312/sr.20251191
dc.identifier.isbn978-3-03868-292-9
dc.identifier.issn1727-3463
dc.identifier.pages10 pages
dc.identifier.urihttps://doi.org/10.2312/sr.20251191
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/sr20251191
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.titleStochastic Ray Tracing of Transparent 3D Gaussiansen_US
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
sr20251191.pdf
Size:
9.1 MB
Format:
Adobe Portable Document Format