An Expectation-Maximization Algorithm for Training Clean Diffusion Models from Corrupted Observations

Understand

Diffusion models excel in solving imaging inverse problems due to their ability to model complex image priors.

• However, their reliance on large, clean datasets for training limits their practical use where clean data is scarce.
• In this paper, we propose EMDiffusion, an expectation-maximization (EM) approach to train diffusion models from corrupted observations.
• Our method alternates between reconstructing clean images from corrupted data using a known diffusion model (E-step) and refining diffusion model weights based on these reconstructions (M-step).