Foundation models for generative computational imaging
Find out more about subscribing to add all events.
Foundation models for generative computational imaging
Fri, 08/05/2026 - 14:00 to 14:30
Location:
Speaker:
Prof Marcelo Pereyra
Affiliation:
HWU
Synopsis:
This talk gives a brief overview of generative computational imaging through the lens of the EPSRC fellowship “Learned Quantitative Stochastic Imaging”, which seeks to build a new mathematical and computational framework for scientific imaging through novel physics-informed deep generative models specialised for Bayesian imaging.
I will highlight recent progress in foundation models for computational imaging, from zero-shot reconstruction with pre-trained latent image–text models to application-specific models learned via unfolding and distillation of Langevin MCMC that deliver excellent posterior samples in just 2–4 neural function evaluations. I will also quickly introduce supervised and self-supervised fine-tuning for settings with limited or no ground truth, as well as theoretical convergence guarantees for iterative generative algorithms. Examples will be drawn from image and video restoration.
Biography:
Marcelo Pereyra is a Professor in Statistics and UKRI EPSRC Open Research Fellow at the School of Mathematical and Computer Sciences of Heriot-Watt University & Maxwell Institute for Mathematical Sciences. He leads pioneering research advancing the statistical foundations of quantitative and scientific imaging, shaping how image data are used as rigorous quantitative evidence, and forging deep connections between statistical, variational, and machine learning approaches to imaging. His leadership and contributions have been recognized through multiple prestigious awards, most recently a five-year fulltime EPSRC Open Fellowship to drive the next generation of breakthroughs in statistical imaging sciences based on physics-informed generative artificial intelligence.
Prof. Pereyra received the SIAM SIGEST Award in Imaging Sciences for his contributions to Bayesian imaging in 2022. He has held Invited Professor positions at Institut Henri Poincaré (Paris, 2019), Université Paris Cité (2022), Ecole Normale Superiéure Lyon (2023), Université Paris Cité (2024) and Centralle Lille (2025). He is also the recipient of a UKRI EPSRC Open Research Fellowship (2025), a Marie Curie Intra-European Fellowship for Career Development (2013), a Brunel Postdoctoral Research Fellowship in Statistics (2012), a Postdoctoral Research Fellowship from French Ministry of Defence (2012), and a Leopold Escande PhD Thesis award from the University of Toulouse (2012).