Spanning Diffusion and Flow-based Posterior Sampling via Exact Gaussian Conditioning

Key points

• Flow-matching and diffusion models are increasingly used as priors for linear inverse problems, however, most methods are bespoke to one class of trajectory prior.1
• We show that many existing guided samplers can be interpreted as instances or approximations of our method, each implicitly using a different trajectory prior and operator in place of the Kalman gain.1
• We demonstrate consistently state-of-the-art level performance across 7 inverse problems over 4 datasets in terms of PSNR and SSIM.1
• Moreover, we demonstrate the utility of this prior control, by showing that confident high correlations (strict priors) work best when observations are less informative, while low correlation is preferred when observations are more informative, reflecting the complementary roles of the prior and likelihood in Bayesian inference.1

Sources (1)

• [1]Spanning Diffusion and Flow-based Posterior Sampling via Exact Gaussian Conditioning
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 9, 04:24 PM

  This work proposes $β$-Flow: a general plug-and-play method indexed by a correlation parameter $β$ that generalises over flow, diffusion, and decorrelated priors, and a confidence parameter $κ$ that controls how strongly the path distribution is enforced.

  Flow-matching and diffusion models are increasingly used as priors for linear inverse problems, however, most methods are bespoke to one class of trajectory prior.

Extractive summary: sentences quoted from the sources.