Bayesian Conditioned Diffusion Models for Inverse Problems

arXiv:2406.09768v1 Announce Type: cross
Abstract: Diffusion models have recently been shown to excel in many image reconstruction tasks that involve inverse problems based on a forward measurement operator. A common framework uses task-agnostic unconditional models that are later post-conditioned for reconstruction, an approach that typically suffers from suboptimal task performance. While task-specific conditional models have also been proposed, current methods heuristically inject measured data as a naive input channel that elicits sampling inaccuracies. Here, we address the optimal conditioning of …

abstract arxiv bayesian cs.ai cs.cv cs.lg diffusion diffusion models excel framework image later measurement performance tasks type while