Denoising Diffusion Probabilistic Models
The DDPM paper presents high-quality image synthesis through learned reversal of a diffusion process. Its formulation connects denoising score matching with a probabilistic latent-variable objective.
Overview. The DDPM paper presents high-quality image synthesis through learned reversal of a diffusion process.
Context. Its formulation connects denoising score matching with a probabilistic latent-variable objective.
Claims and evidence
Claim ledger, 2The DDPM paper presents high-quality image synthesis through learned reversal of a diffusion process.
Its formulation connects denoising score matching with a probabilistic latent-variable objective.