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

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.

14 pages, 8 figures; published in Computer Methods in Applied Mechanics and Engineering

References in corpus (20)

• Score-Based Generative Modeling through Stochastic Differential Equations
• Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains
• fastMRI: An Open Dataset and Benchmarks for Accelerated MRI
• Elucidating the Design Space of Diffusion-Based Generative Models
• FiLM: Visual Reasoning with a General Conditioning Layer
• Solving Inverse Problems in Medical Imaging with Score-Based Generative Models
• Understanding Diffusion Models: A Unified Perspective
• Improving Diffusion Models for Inverse Problems using Manifold Constraints
• L-Sweeps: A scalable, parallel preconditioner for the high-frequency Helmholtz equation
• A Neural Network Warm-Start Approach for the Inverse Acoustic Obstacle Scattering Problem
• WISE: full-Waveform variational Inference via Subsurface Extensions
• Optimal Transport Tools (OTT): A JAX Toolbox for all things Wasserstein
• WISER: multimodal variational inference for full-waveform inversion without dimensionality reduction
• CoCoGen: Physically-Consistent and Conditioned Score-based Generative Models for Forward and Inverse Problems
• Conditional score-based diffusion models for Bayesian inference in infinite dimensions
• Solving the Wide-band Inverse Scattering Problem via Equivariant Neural Networks
• Implicit Neural Representation for Mesh-Free Inverse Obstacle Scattering
• Accurate and Robust Deep Learning Framework for Solving Wave-Based Inverse Problems in the Super-Resolution Regime
• Posterior Sampling with Denoising Oracles via Tilted Transport
• Multi-Frequency Progressive Refinement for Learned Inverse Scattering