A Direct Sampling-Based Deep Learning Approach for Inverse Medium Scattering Problems
This work addresses the problem of recovering unknown scatterers from measured data for researchers in computational physics or imaging, representing an incremental improvement by combining deep learning with an existing direct sampling method.
The authors tackled the inverse medium scattering problem by proposing a direct sampling-based deep learning approach (DSM-DL) that uses a U-Net to learn relationships between index functions and true contrasts, achieving high-quality reconstructions that are computationally efficient and robust to noise.
In this work, we focus on the inverse medium scattering problem (IMSP), which aims to recover unknown scatterers based on measured scattered data. Motivated by the efficient direct sampling method (DSM) introduced in [23], we propose a novel direct sampling-based deep learning approach (DSM-DL)for reconstructing inhomogeneous scatterers. In particular, we use the U-Net neural network to learn the relation between the index functions and the true contrasts. Our proposed DSM-DL is computationally efficient, robust to noise, easy to implement, and able to naturally incorporate multiple measured data to achieve high-quality reconstructions. Some representative tests are carried out with varying numbers of incident waves and different noise levels to evaluate the performance of the proposed method. The results demonstrate the promising benefits of combining deep learning techniques with the DSM for IMSP.