4 papers
BAM! Bayesian Anything Model: a foundation model for generative computational imaging
Alessio Spagnoletti, Charlesquin Kemajou Mbakam, Jonathan Spence +2
Generative models are transforming Bayesian computational imaging, yet the field still lacks physics-aware foundation models. Current practice falls into two camps. Large foundatio…
Learning few-step posterior samplers by unfolding and distillation of diffusion models
Charlesquin Kemajou Mbakam, Jonathan Spence, Marcelo Pereyra
Diffusion models (DMs) have emerged as powerful image priors in Bayesian computational imaging. Two primary strategies have been proposed for leveraging DMs in this context: Plug-a…
Do Bayesian imaging methods report trustworthy probabilities?
David Y. W. Thong, Charlesquin Kemajou Mbakam, Marcelo Pereyra
Bayesian statistics is a cornerstone of imaging sciences, underpinning many and varied approaches from Markov random fields to score-based denoising diffusion models. In addition t…
A stochastic optimisation unadjusted Langevin method for empirical Bayesian estimation in semi-blind image deblurring problems
Charlesquin Kemajou Mbakam, Marcelo Pereyra, Jean-François Giovannelli
This paper presents a novel stochastic optimisation methodology to perform empirical Bayesian inference in semi-blind image deconvolution problems. Given a blurred image and a para…