Physics-Informed Deep Contrast Source Inversion: A Unified Framework for Inverse Scattering Problems

• URL: http://arxiv.org/abs/2508.10555v1
• Date: Thu, 14 Aug 2025 11:50:16 GMT
• Title: Physics-Informed Deep Contrast Source Inversion: A Unified Framework for Inverse Scattering Problems
• Authors: Haoran Sun, Daoqi Liu, Hongyu Zhou, Maokun Li, Shenheng Xu, Fan Yang,
• Abstract summary: This paper proposes a physics-informed deep contrast source inversion framework (DeepCSI) for fast and accurate medium reconstruction.<n>Inspired by contrast source inversion (CSI) and neural operator methods, a residual multilayer perceptron (ResMLP) is employed to model current distributions.<n>DeepCSI achieves high-precision, robust reconstruction under full-data, phaseless data, and multifrequency conditions.
• Score: 23.533153154632082
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Inverse scattering problems are critical in electromagnetic imaging and medical diagnostics but are challenged by their nonlinearity and diverse measurement scenarios. This paper proposes a physics-informed deep contrast source inversion framework (DeepCSI) for fast and accurate medium reconstruction across various measurement conditions. Inspired by contrast source inversion (CSI) and neural operator methods, a residual multilayer perceptron (ResMLP) is employed to model current distributions in the region of interest under different transmitter excitations, effectively linearizing the nonlinear inverse scattering problem and significantly reducing the computational cost of traditional full-waveform inversion. By modeling medium parameters as learnable tensors and utilizing a hybrid loss function that integrates state equation loss, data equation loss, and total variation regularization, DeepCSI establishes a fully differentiable framework for joint optimization of network parameters and medium properties. Compared with conventional methods, DeepCSI offers advantages in terms of simplicity and universal modeling capabilities for diverse measurement scenarios, including phase-less and multi-frequency observation. Simulations and experiments demonstrate that DeepCSI achieves high-precision, robust reconstruction under full-data, phaseless data, and multifrequency conditions, outperforming traditional CSI methods and providing an efficient and universal solution for complex inverse scattering problems.

Related papers

• Multi-Dimensional Visual Data Recovery: Scale-Aware Tensor Modeling and Accelerated Randomized Computation [51.65236537605077]
  We propose a new type of network compression optimization technique, fully randomized tensor network compression (FCTN)<n>FCTN has significant advantages in correlation characterization and transpositional in algebra, and has notable achievements in multi-dimensional data processing and analysis.<n>We derive efficient algorithms with guarantees to solve the formulated models.
  arXiv  Detail & Related papers  (2026-02-13T14:56:37Z)
• Supervised Metric Regularization Through Alternating Optimization for Multi-Regime Physics-Informed Neural Networks [0.0]
  PINNs often face challenges when modeling dynamical systems with sharp regime transitions, such as bifurcations.<n>We propose a Topology-Aware PINN (TAPINN) that aims to mitigate this challenge by the latent space via Supervised Metric Regularization.<n>Preliminary experiments on the Duffing demonstrate that while standard baselines suffer from spectral bias and high-capacity gradient networks overfit, our approach achieves stable convergence with 2.18x lower variance than a multi-output Sobolev Error baseline, and 5x fewer parameters than a hypernetwork-based alternative.
  arXiv  Detail & Related papers  (2026-02-10T17:06:57Z)
• Multimodal Scientific Learning Beyond Diffusions and Flows [9.04041860173466]
  We show that Mixture Density Networks (MDNs) provide a principled yet largely overlooked alternative for multimodal uncertainty quantification in SciML.<n>MDNs impose an inductive bias tailored to low-dimensional, multimodal physics, enabling direct global allocation of probability mass across distinct solution branches.<n>We formalize these insights through a unified probabilistic framework contrasting explicit and implicit distribution networks.
  arXiv  Detail & Related papers  (2026-02-01T01:44:45Z)
• Multi-resolution Physics-Aware Recurrent Convolutional Neural Network for Complex Flows [2.7233737247962786]
  MRPARCv2 is designed to model complex flows by embedding the structure of advection-diffusion-reaction equations.<n>We evaluate the model on a challenging 2D turbulent radiative layer dataset from The Well multi-physics benchmark repository.
  arXiv  Detail & Related papers  (2025-12-04T16:19:10Z)
• A DeepONet joint Neural Tangent Kernel Hybrid Framework for Physics-Informed Inverse Source Problems and Robust Image Reconstruction [13.339856584883242]
  This work presents a novel hybrid approach that integrates Deep Operator Networks (DeepONet) with the Neural Tangent Kernel (NTK) to solve complex inverse problem.<n>The method effectively addresses tasks such as source localization governed by the Navier-Stokes equations and image reconstruction, overcoming challenges related to nonlinearity, sparsity, and noisy data.
  arXiv  Detail & Related papers  (2025-11-01T00:49:20Z)
• Physics-Driven Neural Network for Solving Electromagnetic Inverse Scattering Problems [7.564377962527698]
  A new solution is proposed for inverse scattering problems (ISPs) using a physics-driven neural network (PDNN)<n>PDNN is trained only requiring the input of collected scattered fields and the computation of scattered fields corresponding to predicted solutions.<n>Results demonstrate that the proposed scheme has high reconstruction accuracy and strong stability, even when dealing with composite lossy scatterers.
  arXiv  Detail & Related papers  (2025-07-22T08:04:50Z)
• A Residual Guided strategy with Generative Adversarial Networks in training Physics-Informed Transformer Networks [8.614387766858496]
  We propose a novel Residual Guided Training strategy for Physics-In Transformer via Generative Adrative Network (GAN)<n>Our framework integrates a Transformer to inherently capture temporal correlations through autoregressive processing, coupled with a residual-aware GAN.<n>Experiments on the Allen-Cahn-Gordon, and Navier-Stokes equations demonstrate significant improvements, relative relative MSE reductions of up three orders of magnitude compared to baseline methods.
  arXiv  Detail & Related papers  (2025-07-15T03:45:42Z)
• Compressive Imaging Reconstruction via Tensor Decomposed Multi-Resolution Grid Encoding [50.54887630778593]
  Compressive imaging (CI) reconstruction aims to recover high-dimensional images from low-dimensional measurements compressed.<n>Existing unsupervised representations may struggle to achieve a desired balance between representation ability and efficiency.<n>We propose Decomposed multi-resolution Grid encoding (GridTD), an unsupervised continuous representation framework for CI reconstruction.
  arXiv  Detail & Related papers  (2025-07-10T12:36:20Z)
• Amortized Posterior Sampling with Diffusion Prior Distillation [55.03585818289934]
  Amortized Posterior Sampling is a novel variational inference approach for efficient posterior sampling in inverse problems.<n>Our method trains a conditional flow model to minimize the divergence between the variational distribution and the posterior distribution implicitly defined by the diffusion model.<n>Unlike existing methods, our approach is unsupervised, requires no paired training data, and is applicable to both Euclidean and non-Euclidean domains.
  arXiv  Detail & Related papers  (2024-07-25T09:53:12Z)
• VBIM-Net: Variational Born Iterative Network for Inverse Scattering Problems [9.425567496713366]
  We propose a novel Variational Born Iterative Network, namely, V BIM-Net, to solve the full-wave inverse scattering problems.<n>The proposed V BIM-Net emulates the alternating updates of the total electric field and the contrast in the variational Born iterative method.
  arXiv  Detail & Related papers  (2024-05-29T03:21:09Z)
• Physics-Inspired Degradation Models for Hyperspectral Image Fusion [61.743696362028246]
  Most fusion methods solely focus on the fusion algorithm itself and overlook the degradation models. We propose physics-inspired degradation models (PIDM) to model the degradation of LR-HSI and HR-MSI. Our proposed PIDM can boost the fusion performance of existing fusion methods in practical scenarios.
  arXiv  Detail & Related papers  (2024-02-04T09:07:28Z)
• Neural network analysis of neutron and X-ray reflectivity data: Incorporating prior knowledge for tackling the phase problem [141.5628276096321]
  We present an approach that utilizes prior knowledge to regularize the training process over larger parameter spaces. We demonstrate the effectiveness of our method in various scenarios, including multilayer structures with box model parameterization. In contrast to previous methods, our approach scales favorably when increasing the complexity of the inverse problem.
  arXiv  Detail & Related papers  (2023-06-28T11:15:53Z)
• Implicit Stochastic Gradient Descent for Training Physics-informed Neural Networks [51.92362217307946]
  Physics-informed neural networks (PINNs) have effectively been demonstrated in solving forward and inverse differential equation problems. PINNs are trapped in training failures when the target functions to be approximated exhibit high-frequency or multi-scale features. In this paper, we propose to employ implicit gradient descent (ISGD) method to train PINNs for improving the stability of training process.
  arXiv  Detail & Related papers  (2023-03-03T08:17:47Z)
• Influence Estimation and Maximization via Neural Mean-Field Dynamics [60.91291234832546]
  We propose a novel learning framework using neural mean-field (NMF) dynamics for inference and estimation problems. Our framework can simultaneously learn the structure of the diffusion network and the evolution of node infection probabilities.
  arXiv  Detail & Related papers  (2021-06-03T00:02:05Z)

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.