# Coordinate-Residual Physics-Driven Neural Network for Inverse Scattering Imaging

arXiv: https://arxiv.org/abs/2608.09382 · HTML: https://mlsanity.com/paper/2608.09382/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 34 references that are in the map.
- First posted on arXiv 10 Aug 2026.

## Builds on (most cited first, 8 of 8)

- [DeepNIS: Deep Neural Network for Nonlinear Electromagnetic Inverse Scattering](https://mlsanity.com/paper/1810.03990/) (2018)
- [Physics-guided Loss Functions Improve Deep Learning Performance in Inverse Scattering](https://mlsanity.com/paper/2111.09109/) (2021)
- [SOM-Net: Unrolling the Subspace-based Optimization for Solving Full-wave Inverse Scattering Problems](https://mlsanity.com/paper/2209.03567/) (2022)
- [Neural Born Iteration Method For Solving Inverse Scattering Problems: 2D Cases](https://mlsanity.com/paper/2112.09831/) (2021)
- [Quality-factor inspired deep neural network solver for solving inverse scattering problems](https://mlsanity.com/paper/2504.20504/) (2025)
- [Physics-Driven Neural Network for Solving Electromagnetic Inverse Scattering Problems](https://mlsanity.com/paper/2507.16321/) (2025)
- [Improved Physics-Driven Neural Network to Solve Inverse Scattering Problems](https://mlsanity.com/paper/2512.09333/) (2025)
- [Fast Physics-Driven Untrained Network for Highly Nonlinear Inverse Scattering Problems](https://mlsanity.com/paper/2602.13805/) (2026)

## Abstract (arXiv)

Electromagnetic inverse scattering is a nonlinear and ill-posed computational imaging problem, where accurate reconstruction is challenging due to measurement limitations, noise, and high computational costs, especially for 3-D imaging. Although physics-driven neural networks (PDNNs) reduce the dependence on labeled training data, existing accelerated PDNN frameworks often rely on preliminary reconstruction-based region selection, which may introduce instability when the selected region is inaccurate. In this paper, a coordinate-residual physics-driven neural network (CRPDNN) is proposed for 3-D electromagnetic inverse scattering. CRPDNN represents the unknown complex contrast distribution using normalized spatial coordinates and a residual convolutional network, whose parameters are optimized by enforcing consistency between the measured and model-predicted scattered fields. Unlike existing subregion-accelerated PDNN approaches, CRPDNN does not require a preliminary reconstruction, thereby avoiding dependence on its accuracy. For the reported noise-free 3-D synthetic cases, CRPDNN achieves an average relative error of 2.10%, compared with 7.97% for CSI and 3.99% for L2/3-FBE-WCIE, while providing approximately 5.5- and 12.1-fold speedups over the two baselines, respectively. Additional 2-D comparisons further demonstrate its stability and computational efficiency relative to existing PDNN frameworks. CRPDNN also maintains reliable reconstruction performance under noisy measurements, and the 3-D Fresnel experiments further indicate its potential for practical imaging applications.