Generalizable Neural Electromagnetic Inverse Scattering

• URL: http://arxiv.org/abs/2506.21349v3
• Date: Tue, 29 Jul 2025 03:15:17 GMT
• Title: Generalizable Neural Electromagnetic Inverse Scattering
• Abstract summary: Solving Electromagnetic Inverse Scattering Problems (EISP) is fundamental in applications such as medical imaging.<n>We revisit EISP from a physics-informed perspective, reformulating it as a two stage inverse transmission-scattering process.<n>We propose the first generalizable physics-driven framework for EISP, comprising a current estimator and a permittivity solver.
• Score: 14.57298958010568
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Solving Electromagnetic Inverse Scattering Problems (EISP) is fundamental in applications such as medical imaging, where the goal is to reconstruct the relative permittivity from scattered electromagnetic field. This inverse process is inherently ill-posed and highly nonlinear, making it particularly challenging. A recent machine learning-based approach, Img-Interiors, shows promising results by leveraging continuous implicit functions. However, it requires case-specific optimization, lacks generalization to unseen data, and fails under sparse transmitter setups (e.g., with only one transmitter). To address these limitations, we revisit EISP from a physics-informed perspective, reformulating it as a two stage inverse transmission-scattering process. This formulation reveals the induced current as a generalizable intermediate representation, effectively decoupling the nonlinear scattering process from the ill-posed inverse problem. Built on this insight, we propose the first generalizable physics-driven framework for EISP, comprising a current estimator and a permittivity solver, working in an end-to-end manner. The current estimator explicitly learns the induced current as a physical bridge between the incident and scattered field, while the permittivity solver computes the relative permittivity directly from the estimated induced current. This design enables data-driven training and generalizable feed-forward prediction of relative permittivity on unseen data while maintaining strong robustness to transmitter sparsity. Extensive experiments show that our method outperforms state-of-the-art approaches in reconstruction accuracy, generalization, and robustness. This work offers a fundamentally new perspective on electromagnetic inverse scattering and represents a major step toward cost-effective practical solutions for electromagnetic imaging.

Related papers

• Stokes-Informed Diffusion for Robust Linear Polarization Estimation [49.459667092743445]
  GenPolar is a Stokes-informed diffusion framework grounded in the Mueller formalism from an intensity observation.<n>It achieves state-of-the-art performance in both DoLP fidelity and AoP stability.<n>These improvements translate to significant and consistent gains in downstream applications, including material detection and de-reflection.
  arXiv  Detail & Related papers  (2026-07-23T11:56:15Z)
• DOC-GS: Dual-Domain Observation and Calibration for Reliable Sparse-View Gaussian Splatting [80.43237927269575]
  In this paper, we revisit sparse-view 3DGS reconstruction from a new perspective.<n>We identify the core challenge as the unobservability of Gaussian primitive reliability.<n>Motivated by this observation, we propose a unified Dual-domain Observation and geometrics in rendered images framework.
  arXiv  Detail & Related papers  (2026-04-08T07:01:24Z)
• JetPrism: diagnosing convergence for generative simulation and inverse problems in nuclear physics [0.5823178881486669]
  High-fidelity Monte Carlo simulations and complex inverse problems are computationally intensive yet essential for robust data analysis.<n> Conditional Flow Matching (CFM) offers a mathematically robust approach to accelerating these tasks, but we demonstrate its standard training loss is fundamentally misleading.<n>In rigorous physics applications, CFM loss plateaus prematurely, serving as an unreliable indicator of true convergence and physical fidelity.
  arXiv  Detail & Related papers  (2026-04-01T18:36:47Z)
• Autonomous battery research: Principles of heuristic operando experimentation [5.681725902637965]
  Heuristic Operando experiments is a framework where an AI pilot leverages physics-based digital twins to actively steer the beamline to predict and deterministically capture rare events.<n>By focusing measurements only on mechanistically decisive moments, this framework simultaneously mitigates beam damage and drastically reduces data redundancy.
  arXiv  Detail & Related papers  (2025-12-29T18:08:08Z)
• Physics-Guided Conditional Diffusion Networks for Microwave Image Reconstruction [0.6117371161379209]
  A conditional latent-diffusion based framework for solving the electromagnetic inverse scattering problem is introduced.<n>The proposed model generates multiple plausible permittivity maps conditioned on measured scattered-field data.<n>A forward electromagnetic solver is integrated into the reconstruction pipeline as a physics-based evaluation mechanism.
  arXiv  Detail & Related papers  (2025-10-29T17:34:10Z)
• ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving [64.42138266293202]
  ResAD is a Normalized Residual Trajectory Modeling framework.<n>It reframes the learning task to predict the residual deviation from an inertial reference.<n>On the NAVSIM benchmark, ResAD achieves a state-of-the-art PDMS of 88.6 using a vanilla diffusion policy.
  arXiv  Detail & Related papers  (2025-10-09T17:59:36Z)
• Revisiting Multivariate Time Series Forecasting with Missing Values [65.30332997607141]
  Missing values are common in real-world time series.<n>Current approaches have developed an imputation-then-prediction framework that uses imputation modules to fill in missing values, followed by forecasting on the imputed data.<n>This framework overlooks a critical issue: there is no ground truth for the missing values, making the imputation process susceptible to errors that can degrade prediction accuracy.<n>We introduce Consistency-Regularized Information Bottleneck (CRIB), a novel framework built on the Information Bottleneck principle.
  arXiv  Detail & Related papers  (2025-09-27T20:57:48Z)
• RadioDiff-$k^2$: Helmholtz Equation Informed Generative Diffusion Model for Multi-Path Aware Radio Map Construction [69.96295462931168]
  We propose a physics-informed generative learning approach, termed RadioDiff-$bmk2$, for accurate and efficient multipath-aware radio map (RM) construction.<n>We establish a direct correspondence between EM singularities, which correspond to the critical spatial features influencing wireless propagation, and regions defined by negative wave numbers in the Helmholtz equation.
  arXiv  Detail & Related papers  (2025-04-22T06:28:13Z)
• DispFormer: A Pretrained Transformer Incorporating Physical Constraints for Dispersion Curve Inversion [56.64622091009756]
  This study introduces DispFormer, a transformer-based neural network for $v_s$ profile inversion from Rayleigh-wave phase and group dispersion curves.<n>DispFormer processes dispersion data independently at each period, allowing it to handle varying lengths without requiring network modifications or strict alignment between training and testing datasets.
  arXiv  Detail & Related papers  (2025-01-08T09:08:24Z)
• CPFI-EIT: A CNN-PINN Framework for Full-Inverse Electrical Impedance Tomography on Non-Smooth Conductivity Distributions [0.0]
  We introduce a hybrid learning framework that combines convolutional neural networks (CNNs) and physics-informed neural networks (PINNs)<n>EIT is a noninvasive imaging technique that reconstructs the spatial distribution of internal conductivity based on boundary voltage measurements from injected currents.
  arXiv  Detail & Related papers  (2024-12-10T10:48:43Z)
• Diff-INR: Generative Regularization for Electrical Impedance Tomography [6.7667436349597985]
  Electrical Impedance Tomography (EIT) reconstructs conductivity distributions within a body from boundary measurements. EIT reconstruction is hindered by its ill-posed nonlinear inverse problem, which complicates accurate results. We propose Diff-INR, a novel method that combines generative regularization with Implicit Neural Representations (INR) through a diffusion model.
  arXiv  Detail & Related papers  (2024-09-06T14:21:23Z)
• Imaging Interiors: An Implicit Solution to Electromagnetic Inverse Scattering Problems [74.28677741399966]
  Electromagnetic Inverse Scattering Problems (EISP) have gained wide applications in computational imaging. This paper tackles those challenges in EISP via an implicit approach. Our approach outperforms existing methods on standard benchmark datasets.
  arXiv  Detail & Related papers  (2024-07-12T15:25:54Z)
• DeltaPhi: Learning Physical Trajectory Residual for PDE Solving [54.13671100638092]
  We propose and formulate the Physical Trajectory Residual Learning (DeltaPhi) We learn the surrogate model for the residual operator mapping based on existing neural operator networks. We conclude that, compared to direct learning, physical residual learning is preferred for PDE solving.
  arXiv  Detail & Related papers  (2024-06-14T07:45:07Z)
• Unified, Verifiable Neural Simulators for Electromagnetic Wave Inverse Problems [1.6795461001108096]
  We show a single, unified model capable of addressing scattering simulations with thousands of DoFs, of any wavelength, any illumination wavefront, and freeform materials. Our findings demonstrate a path to universal, verifiably accurate neural surrogates for existing scattering simulators.
  arXiv  Detail & Related papers  (2024-03-31T03:23:29Z)
• Large-Scale OD Matrix Estimation with A Deep Learning Method [70.78575952309023]
  The proposed method integrates deep learning and numerical optimization algorithms to infer matrix structure and guide numerical optimization. We conducted tests to demonstrate the good generalization performance of our method on a large-scale synthetic dataset.
  arXiv  Detail & Related papers  (2023-10-09T14:30:06Z)
• Learning Functional Transduction [9.926231893220063]
  We show that transductive regression principles can be meta-learned through gradient descent to form efficient in-context neural approximators. We demonstrate the benefit of our meta-learned transductive approach to model complex physical systems influenced by varying external factors with little data.
  arXiv  Detail & Related papers  (2023-02-01T09:14:28Z)
• Transformer Meets Boundary Value Inverse Problems [4.165221477234755]
  Transformer-based deep direct sampling method is proposed for solving a class of boundary value inverse problem. A real-time reconstruction is achieved by evaluating the learned inverse operator between carefully designed data and reconstructed images.
  arXiv  Detail & Related papers  (2022-09-29T17:45:25Z)
• Extension of Dynamic Mode Decomposition for dynamic systems with incomplete information based on t-model of optimal prediction [69.81996031777717]
  The Dynamic Mode Decomposition has proved to be a very efficient technique to study dynamic data. The application of this approach becomes problematic if the available data is incomplete because some dimensions of smaller scale either missing or unmeasured. We consider a first-order approximation of the Mori-Zwanzig decomposition, state the corresponding optimization problem and solve it with the gradient-based optimization method.
  arXiv  Detail & Related papers  (2022-02-23T11:23:59Z)
• Quantum thermoelectric transmission functions with minimal current fluctuations [0.0]
  Thermodynamic uncertainty relations (TURs) represent a benchmark result in nonequilibrium physics.<n>We rigorously demonstrate that the transmission function which maximizes the reliability of thermoelectric devices is a collection of boxcar functions.<n>This allows us to show that TURs can be violated by arbitrarily large amounts, depending on the temperature and chemical potential gradients.
  arXiv  Detail & Related papers  (2021-06-18T16:18:19Z)
• Leveraging Global Parameters for Flow-based Neural Posterior Estimation [90.21090932619695]
  Inferring the parameters of a model based on experimental observations is central to the scientific method. A particularly challenging setting is when the model is strongly indeterminate, i.e., when distinct sets of parameters yield identical observations. We present a method for cracking such indeterminacy by exploiting additional information conveyed by an auxiliary set of observations sharing global parameters.
  arXiv  Detail & Related papers  (2021-02-12T12:23:13Z)
• Accurately computing electronic properties of a quantum ring [0.08564085951364296]
  We provide an experimental blueprint for an accurate condensed-matter simulator using eighteen superconducting qubits. We benchmark the underlying method by reconstructing the single-particle band-structure of a one-dimensional wire. We synthesize magnetic flux and disordered local potentials, two key tenets of a condensed-matter system.
  arXiv  Detail & Related papers  (2020-12-02T01:42:20Z)
• Statistical control for spatio-temporal MEG/EEG source imaging with desparsified multi-task Lasso [102.84915019938413]
  Non-invasive techniques like magnetoencephalography (MEG) or electroencephalography (EEG) offer promise of non-invasive techniques. The problem of source localization, or source imaging, poses however a high-dimensional statistical inference challenge. We propose an ensemble of desparsified multi-task Lasso (ecd-MTLasso) to deal with this problem.
  arXiv  Detail & Related papers  (2020-09-29T21:17:16Z)
• Targeted free energy estimation via learned mappings [66.20146549150475]
  Free energy perturbation (FEP) was proposed by Zwanzig more than six decades ago as a method to estimate free energy differences. FEP suffers from a severe limitation: the requirement of sufficient overlap between distributions. One strategy to mitigate this problem, called Targeted Free Energy Perturbation, uses a high-dimensional mapping in configuration space to increase overlap.
  arXiv  Detail & Related papers  (2020-02-12T11:10:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.