Deep Injective Prior for Inverse Scattering
This addresses the need for robust, uncertainty-aware methods in inverse scattering for applications like medical imaging or material characterization, though it is incremental as it builds on existing deep learning approaches.
The paper tackles the problem of reconstructing object permittivity in electromagnetic inverse scattering by proposing a data-driven framework using deep generative models as a regularizer, which outperforms traditional iterative solvers for strong scatterers and matches supervised learning methods like U-Net in reconstruction quality.
In electromagnetic inverse scattering, the goal is to reconstruct object permittivity using scattered waves. While deep learning has shown promise as an alternative to iterative solvers, it is primarily used in supervised frameworks which are sensitive to distribution drift of the scattered fields, common in practice. Moreover, these methods typically provide a single estimate of the permittivity pattern, which may be inadequate or misleading due to noise and the ill-posedness of the problem. In this paper, we propose a data-driven framework for inverse scattering based on deep generative models. Our approach learns a low-dimensional manifold as a regularizer for recovering target permittivities. Unlike supervised methods that necessitate both scattered fields and target permittivities, our method only requires the target permittivities for training; it can then be used with any experimental setup. We also introduce a Bayesian framework for approximating the posterior distribution of the target permittivity, enabling multiple estimates and uncertainty quantification. Extensive experiments with synthetic and experimental data demonstrate that our framework outperforms traditional iterative solvers, particularly for strong scatterers, while achieving comparable reconstruction quality to state-of-the-art supervised learning methods like the U-Net.