Get Started

3D Gaussian Splatting from Scratch

A scene is a cloud of millions of 3D Gaussians. Each one has a position, orientation, scale, opacity, and a colour that depends on viewing direction. Rasterise them, backprop through the rasterisation, done.

90 minutesBuildPythonMembers

Learning Objectives

  • Explain why 3D Gaussian Splatting replaced NeRF as the production default for photorealistic 3D reconstruction in 2026
  • State the six per-Gaussian parameters (position, rotation quaternion, scale, opacity, spherical harmonics colour, optional feature) and how many floats each contributes
  • Implement a 2D Gaussian splatting rasterizer from scratch using alpha compositing, then show how the 3D case projects to the same loop
  • Use nerfstudiogsplator SuperSplat to reconstruct a scene from 20-50 photos and export to the KHR_gaussian_splatting glTF extension or the OpenUSD 26.03 UsdVolParticleField3DGaussianSplat schema