2026
Normalization-equivariant Diffusion Models: Learning Posterior Samplers From Noisy And Partial Measurements
ICML 2026poster
Diffusion models (DMs) are a powerful framework for image generation and restoration. However, existing DMs are primarily trained in a supervised manner by using a large corpus of clean images. This poses fundamental challenges in many real-world scenarios, where acquiring noise-free data is hard or…