StochasticSplats: Stochastic Rasterization for Sorting-Free 3D Gaussian Splatting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kheradmand, Shakiba, Vicini, Delio, Kopanas, George, Lagun, Dmitry, Yi, Kwang Moo, Matthews, Mark, Tagliasacchi, Andrea
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915219733741568
author Kheradmand, Shakiba
Vicini, Delio
Kopanas, George
Lagun, Dmitry
Yi, Kwang Moo
Matthews, Mark
Tagliasacchi, Andrea
author_facet Kheradmand, Shakiba
Vicini, Delio
Kopanas, George
Lagun, Dmitry
Yi, Kwang Moo
Matthews, Mark
Tagliasacchi, Andrea
contents 3D Gaussian splatting (3DGS) is a popular radiance field method, with many application-specific extensions. Most variants rely on the same core algorithm: depth-sorting of Gaussian splats then rasterizing in primitive order. This ensures correct alpha compositing, but can cause rendering artifacts due to built-in approximations. Moreover, for a fixed representation, sorted rendering offers little control over render cost and visual fidelity. For example, and counter-intuitively, rendering a lower-resolution image is not necessarily faster. In this work, we address the above limitations by combining 3D Gaussian splatting with stochastic rasterization. Concretely, we leverage an unbiased Monte Carlo estimator of the volume rendering equation. This removes the need for sorting, and allows for accurate 3D blending of overlapping Gaussians. The number of Monte Carlo samples further imbues 3DGS with a way to trade off computation time and quality. We implement our method using OpenGL shaders, enabling efficient rendering on modern GPU hardware. At a reasonable visual quality, our method renders more than four times faster than sorted rasterization.
format Preprint
id arxiv_https___arxiv_org_abs_2503_24366
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle StochasticSplats: Stochastic Rasterization for Sorting-Free 3D Gaussian Splatting
Kheradmand, Shakiba
Vicini, Delio
Kopanas, George
Lagun, Dmitry
Yi, Kwang Moo
Matthews, Mark
Tagliasacchi, Andrea
Computer Vision and Pattern Recognition
Graphics
3D Gaussian splatting (3DGS) is a popular radiance field method, with many application-specific extensions. Most variants rely on the same core algorithm: depth-sorting of Gaussian splats then rasterizing in primitive order. This ensures correct alpha compositing, but can cause rendering artifacts due to built-in approximations. Moreover, for a fixed representation, sorted rendering offers little control over render cost and visual fidelity. For example, and counter-intuitively, rendering a lower-resolution image is not necessarily faster. In this work, we address the above limitations by combining 3D Gaussian splatting with stochastic rasterization. Concretely, we leverage an unbiased Monte Carlo estimator of the volume rendering equation. This removes the need for sorting, and allows for accurate 3D blending of overlapping Gaussians. The number of Monte Carlo samples further imbues 3DGS with a way to trade off computation time and quality. We implement our method using OpenGL shaders, enabling efficient rendering on modern GPU hardware. At a reasonable visual quality, our method renders more than four times faster than sorted rasterization.
title StochasticSplats: Stochastic Rasterization for Sorting-Free 3D Gaussian Splatting
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2503.24366