From Volume Rendering to 3D Gaussian Splatting: Theory and Applications
This is an incremental tutorial paper for researchers and practitioners in computer vision and graphics, summarizing existing 3DGS methods rather than introducing new techniques.
This tutorial provides an overview of 3D Gaussian Splatting (3DGS) for 3D reconstruction from posed images, covering its pipeline, limitations like high memory footprint and baked lighting, and applications in surface reconstruction and avatar modeling.
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.