Back-Projection Diffusion: Solving the Wideband Inverse Scattering Problem with Diffusion Models

TL;DR

This paper introduces Wideband Back-Projection Diffusion, a probabilistic framework that leverages diffusion models and physics-based transformations to produce accurate, efficient, and symmetry-aware reconstructions in inverse scattering problems.

Contribution

It proposes a novel end-to-end diffusion-based approach combining physics-inspired data transformation and learned score functions for inverse scattering reconstruction.

Findings

Achieves high-accuracy reconstructions with low sample complexity.

Capable of recovering sub-Nyquist features in multiple-scattering regimes.

Number of parameters scales sub-linearly with resolution.

Abstract

We present Wideband Back-Projection Diffusion, an end-to-end probabilistic framework for approximating the posterior distribution induced by the inverse scattering map from wideband scattering data. This framework produces highly accurate reconstructions, leveraging conditional diffusion models to draw samples, and also honors the symmetries of the underlying physics of wave-propagation. The procedure is factored into two steps: the first step, inspired by the filtered back-propagation formula, transforms data into a physics-based latent representation, while the second step learns a conditional score function conditioned on this latent representation. These two steps individually obey their associated symmetries and are amenable to compression by imposing the rank structure found in the filtered back-projection formula. Empirically, our framework has both low sample and computational complexity, with its number of parameters scaling only sub-linearly with the target resolution, and has stable training dynamics. It provides sharp reconstructions effortlessly and is capable of recovering even sub-Nyquist features in the multiple-scattering regime.