Diffusion Models — Noise Process & Denoising

Forward: q(xₜ|x₀) = N(√ᾱₜ x₀, (1-ᾱₜ)I) · Reverse: score matching

Controls

Forward: Gradually add Gaussian noise over T steps. At t=T: pure noise N(0,I).

Reverse: A neural network predicts the score ∇logp(xₜ) to denoise step-by-step.

DDPM: xₜ₋₁ = (xₜ - β̃ₜ·ε̂)/√(1-βₜ) + σₜz