AI RESEARCH
Noise-Adaptive Diffusion Sampling for Inverse Problems Without Task-Specific Tuning
arXiv CS.LG
•
ArXi:2604.16919v1 Announce Type: new Diffusion models (DMs) have recently shown remarkable performance on inverse problems (IPs). Optimization-based methods can fast solve IPs using DMs as powerful regularizers, but they are susceptible to local minima and noise overfitting. Although DMs can provide strong priors for Bayesian approaches, enforcing measurement consistency during the denoising process leads to manifold infeasibility issues.