Virtual Memory for 3D Gaussian Splatting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Haberl, Jonathan, Fleck, Philipp, Arth, Clemens
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916809478766592
author Haberl, Jonathan
Fleck, Philipp
Arth, Clemens
author_facet Haberl, Jonathan
Fleck, Philipp
Arth, Clemens
contents 3D Gaussian Splatting represents a breakthrough in the field of novel view synthesis. It establishes Gaussians as core rendering primitives for highly accurate real-world environment reconstruction. Recent advances have drastically increased the size of scenes that can be created. In this work, we present a method for rendering large and complex 3D Gaussian Splatting scenes using virtual memory. By leveraging well-established virtual memory and virtual texturing techniques, our approach efficiently identifies visible Gaussians and dynamically streams them to the GPU just in time for real-time rendering. Selecting only the necessary Gaussians for both storage and rendering results in reduced memory usage and effectively accelerates rendering, especially for highly complex scenes. Furthermore, we demonstrate how level of detail can be integrated into our proposed method to further enhance rendering speed for large-scale scenes. With an optimized implementation, we highlight key practical considerations and thoroughly evaluate the proposed technique and its impact on desktop and mobile devices.
format Preprint
id arxiv_https___arxiv_org_abs_2506_19415
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Virtual Memory for 3D Gaussian Splatting
Haberl, Jonathan
Fleck, Philipp
Arth, Clemens
Graphics
Computer Vision and Pattern Recognition
Human-Computer Interaction
3D Gaussian Splatting represents a breakthrough in the field of novel view synthesis. It establishes Gaussians as core rendering primitives for highly accurate real-world environment reconstruction. Recent advances have drastically increased the size of scenes that can be created. In this work, we present a method for rendering large and complex 3D Gaussian Splatting scenes using virtual memory. By leveraging well-established virtual memory and virtual texturing techniques, our approach efficiently identifies visible Gaussians and dynamically streams them to the GPU just in time for real-time rendering. Selecting only the necessary Gaussians for both storage and rendering results in reduced memory usage and effectively accelerates rendering, especially for highly complex scenes. Furthermore, we demonstrate how level of detail can be integrated into our proposed method to further enhance rendering speed for large-scale scenes. With an optimized implementation, we highlight key practical considerations and thoroughly evaluate the proposed technique and its impact on desktop and mobile devices.
title Virtual Memory for 3D Gaussian Splatting
topic Graphics
Computer Vision and Pattern Recognition
Human-Computer Interaction
url https://arxiv.org/abs/2506.19415