Marcelo Pereyra | Heriot-Watt University

Marcelo Pereyra | Research group

Maxwell Insitute for Mathematical Sciences
School of Mathematical and Computer Sciences, Heriot-Watt University

Research group

My research group and network of collaborators are central to my research activities and why I find research so enjoyable and stimulating. I list below my current and former PhD students and postdocs. For information about my collaborations, please my publications and my g scholar profile.

Our research is mainly about new mathematical theory, methods and algorithms to solve challenging inverse problems related to mathematical and computational imaging. We are particularly interested in new Bayesian analysis and computation approaches, and in the synergy between the Bayesian, the variational, and the machine learning paradigms for imaging methodology. Our research is in part funded by two UKRI EPSRC projects (see BOLT and BLOOM).

Postdocs

Dr David Thong, Heriot-Watt University & Maxwell Institute of Mathematical Sciences, Bayesian model selection and calibration for computational imaging (see BOLT).
Dr Cecilia Tarpau, Heriot-Watt University & Maxwell Institute of Mathematical Sciences, Bayesian computation for low-photon imaging (see BLOOM).
Dr Paul Dobson, University of Edinburgh & Maxwell Institute of Mathematical Sciences, Bayesian computation for low-photon imaging (see BLOOM).

PhD students

Luis Vargas Mieles (with Dr. Kostas Zygalakis), University of Edinburgh & Maxwell Institute of Mathematical Sciences, Accelerating Bayesian computational imaging.
Matthew Holden (with Dr. Kostas Zygalakis), Heriot-Watt University & Maxwell Institute of Mathematical Sciences, Incorporating deep learning approaches in high-dimensional Bayesian inference methods. Application to satellite imaging.
Rémi Laumont (with DR Andrés Almansa and Prof. Julie Delon), University of Paris, Digital photographic image restoration: Bayesian models and neural networks.
Savvas Melidonis (with Dr. Kostas Zygalakis and Dr Yoann Altmann), Heriot-Watt University & Maxwell Institute of Mathematical Sciences, Bayesian computation for low-photon imaging.
Charlesquin Kemajou (with Prof. Jean-François Giovannelli), Heriot-Watt University & Maxwell Institute of Mathematical Sciences, Bayesian and machine learning methods for blind and semi-blind inverse problems in computational imaging.
Teresa Klatzer (with Dr. Kostas Zygalakis and Dr Yoann Altmann), University of Edinburgh & Maxwell Institute of Mathematical Sciences, Bayesian computation for low-photon imaging.

LEXCI

I am a principal investigator in the UKRI EPSRC Project Learned Exascale Computational Imaging (LEXCI), led by Prof. Jason McEwen, that will develop novel highly parallelized and distributed hybrid algorithms that blend model-based and deep learning computational imaging approaches, with special attention to scalability, uncertainty quantification, and applications in radio astronomy.

Former PhD students

Dr. Ana Fernandez Vidal (with Prof. Gavin Gibson), Heriot-Watt University, Bayesian computation in imaging inverse problems with partially unknown models, Sep. 2020.
Dr Benjamin Harroue (with Prof. Jean-François Giovannelli), University of Bordeaux, Approche bayésienne pour la sélection de modèles. Application à la restauration d’image , Sep. 2020.