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

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Matias, Vitor Pereira, Perazzo, Daniel, Silva, Vinicius, Raposo, Alberto, Velho, Luiz, Paiva, Afonso, Novello, Tiago
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912930627321856
author Matias, Vitor Pereira
Perazzo, Daniel
Silva, Vinicius
Raposo, Alberto
Velho, Luiz
Paiva, Afonso
Novello, Tiago
author_facet Matias, Vitor Pereira
Perazzo, Daniel
Silva, Vinicius
Raposo, Alberto
Velho, Luiz
Paiva, Afonso
Novello, Tiago
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_18101
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle From Volume Rendering to 3D Gaussian Splatting: Theory and Applications
Matias, Vitor Pereira
Perazzo, Daniel
Silva, Vinicius
Raposo, Alberto
Velho, Luiz
Paiva, Afonso
Novello, Tiago
Computer Vision and Pattern Recognition
68-01
A.1
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.
title From Volume Rendering to 3D Gaussian Splatting: Theory and Applications
topic Computer Vision and Pattern Recognition
68-01
A.1
url https://arxiv.org/abs/2510.18101