We integrate physical models with deep learning and advanced optimisation methods to create powerful, physics-constrained image reconstruction methods. Combining the interpretability of physics-based methods, the flexibility of data-driven techniques, and the efficiency of advanced optimization algorithms, this hybrid approach provides theoretically grounded solutions for complex imaging problems with limited training data.

Luca Calatroni DIBRIS, Università di Genova

Kostas Papafitsoros QMLU, UK
Samuel Vaiter CNRS, France
Camille Castera Université de Bordeaux, France
Samuel Hurault ENS, Paris, France
Kostas Papafitsoros QMUL, London, UK
Audrey Repetti Heriot-Watt University, Edinburgh, UK