How Splatting Works
LESSONINTERMEDIATE
📖1 min read
Module Overview
| Est. time | 45 minutes |
| Type | Foundations |
| Prerequisites | Module 01 |
This lesson is a stub. Content to be developed.
Planned Content
Gaussian Representation
- Position (mean), covariance (shape), opacity, color (spherical harmonics)
- What makes a Gaussian "anisotropic"
- How parameters are stored and optimized
The Optimization Process
- Starting from a sparse point cloud (COLMAP output)
- Gradient descent on Gaussian parameters
- Adaptive density control: splitting, cloning, pruning
- Loss functions: L1 + D-SSIM
Rendering
- Tile-based rasterization (not ray marching)
- Alpha blending — splatting Gaussians onto the image plane
- Why it's fast: no per-pixel ray queries
3DGS vs. NeRF
- NeRF: implicit, continuous, slow to render
- 3DGS: explicit, discrete, real-time rendering
- Trade-offs in quality, speed, and controllability
Knowledge Check
(To be written)
Resources
KB Pages
External
- 3D Gaussian Splatting paper — Section 3: Overview
- Gaussian Splatting explained (YouTube) — Technical walkthrough