Redirecting to original paper in 30 seconds...
Click below to go immediately or wait for automatic redirect
📄 Abstract
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.
Authors (7)
Vitor Pereira Matias
Daniel Perazzo
Vinicius Silva
Alberto Raposo
Luiz Velho
Afonso Paiva
+1 more
Submitted
October 20, 2025
Key Contributions
This tutorial provides a comprehensive overview of 3D Gaussian Splatting (3DGS), a technique transforming 3D reconstruction and rendering. It details the 3DGS pipeline, explores solutions to its limitations (high memory, baked lighting), and surveys applications in surface reconstruction, avatar modeling, and content generation, highlighting its real-time rendering capabilities.
Business Value
Dramatically improves the efficiency and quality of 3D content creation and rendering pipelines, enabling more immersive VR/AR experiences, realistic game environments, and faster 3D asset generation.