Paper ID: 2410.21556

Super-resolution in disordered media using neural networks

Alexander Christie, Matan Leibovitch, Miguel Moscoso, Alexei Novikov, George Papanicolaou, Chrysoula Tsogka

We propose a methodology that exploits large and diverse data sets to accurately estimate the ambient medium's Green's functions in strongly scattering media. Given these estimates, obtained with and without the use of neural networks, excellent imaging results are achieved, with a resolution that is better than that of a homogeneous medium. This phenomenon, also known as super-resolution, occurs because the ambient scattering medium effectively enhances the physical imaging aperture.

Submitted: Oct 28, 2024