Variational inference for computational imaging inverse problems

Tonolini, F. , Radford, J. , Turpin, A. , Faccio, D. and Murray-Smith, R. (2020) Variational inference for computational imaging inverse problems. Journal of Machine Learning Research, 21(179), pp. 1-46.

[img] Text
223297.pdf - Published Version
Available under License Creative Commons Attribution.


Publisher's URL:


Machine learning methods for computational imaging require uncertainty estimation to be reliable in real settings. While Bayesian models offer a computationally tractable way of recovering uncertainty, they need large data volumes to be trained, which in imaging applications implicates prohibitively expensive collections with specific imaging instruments. This paper introduces a novel framework to train variational inference for inverse problems exploiting in combination few experimentally collected data, domain expertise and existing image data sets. In such a way, Bayesian machine learning models can solve imaging inverse problems with minimal data collection efforts. Extensive simulated experiments show the advantages of the proposed framework. The approach is then applied to two real experimental optics settings: holographic image reconstruction and imaging through highly scattering media. In both settings, state of the art reconstructions are achieved with little collection of training data.

Item Type:Articles
Glasgow Author(s) Enlighten ID:Murray-Smith, Professor Roderick and Faccio, Professor Daniele and Tonolini, Francesco and Radford, Jack and Turpin, Dr Alex
Authors: Tonolini, F., Radford, J., Turpin, A., Faccio, D., and Murray-Smith, R.
College/School:College of Science and Engineering > School of Computing Science
College of Science and Engineering > School of Physics and Astronomy
Journal Name:Journal of Machine Learning Research
Publisher:Microtome Publishing
ISSN (Online):1533-7928
Copyright Holders:Copyright © 2020 Francesco Tonolini, Jack Radford, Alex Turpin, Daniele Faccio and Roderick Murray-Smith
First Published:First published in Journal of Machine Learning Research 21(179): 1-46
Publisher Policy:Reproduced under a Creative Commons License

University Staff: Request a correction | Enlighten Editors: Update this record