Slides part 1: Introduction; Volume Rendering; EWA splatting eq from Volume Rendering;
Slides part 2: 3D Gaussian Splatting; Some Works Regarding Extensions and Applications.
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.
Overview of the 3DGS pipeline. The process begins (left) with a set of posed images captured around an object, from which a sparse SfM point cloud is reconstructed. Gaussians are then initialized over this point cloud and optimized (center) through differentiable volumetric splatting. The rendered image is compared to the input views using an photometric loss, whose gradient is used to update the Gaussian parameters. To enhance spatial coverage and avoid under- or over-representation, 3DGS incorporates an adaptation step (right) that dynamically adds (via splitting or cloning) or removes Gaussians during training.
@inproceedings{sibgrapi_3dgs_tutorial_2025,
title={From Volume Rendering to 3D Gaussian Splatting: Theory and Applications},
author={Matias, Vitor and Perazzo, Daniel and Silva, Vinícius and Raposo, Alberto and Velho, Luiz and Paiva, Afonso and Novello, Tiago},
booktitle={SIBGRAPI},
year={2025}
}