English

From Volume Rendering to 3D Gaussian Splatting: Theory and Applications

Computer Vision and Pattern Recognition 2026-03-02 v1

Abstract

The problem of 3D reconstruction from posed images is undergoing a fundamental transformation, driven by continuous advances in 3D Gaussian Splatting (3DGS). By modeling scenes explicitly as collections of 3D Gaussians, 3DGS enables efficient rasterization through volumetric splatting, offering thus a seamless integration with common graphics pipelines. Despite its real-time rendering capabilities for novel view synthesis, 3DGS suffers from a high memory footprint, the tendency to bake lighting effects directly into its representation, and limited support for secondary-ray effects. This tutorial provides a concise yet comprehensive overview of the 3DGS pipeline, starting from its splatting formulation and then exploring the main efforts in addressing its limitations. Finally, we survey a range of applications that leverage 3DGS for surface reconstruction, avatar modeling, animation, and content generation-highlighting its efficient rendering and suitability for feed-forward pipelines.

Keywords

Cite

@article{arxiv.2510.18101,
  title  = {From Volume Rendering to 3D Gaussian Splatting: Theory and Applications},
  author = {Vitor Pereira Matias and Daniel Perazzo and Vinicius Silva and Alberto Raposo and Luiz Velho and Afonso Paiva and Tiago Novello},
  journal= {arXiv preprint arXiv:2510.18101},
  year   = {2026}
}

Comments

Accepted at the Conference on Graphics, Patterns and Images (SIBGRAPI), math focused, 5 equations, 5 Figure, 5 pages of text and 1 of bibligraphy