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
alphacompositing, then show how the 3D case projects to the same loop - Use
nerfstudiogsplatorSuperSplatto reconstruct a scene from 20-50 photos and export to theKHR_gaussian_splattingglTF extension or the OpenUSD 26.03UsdVolParticleField3DGaussianSplatschema