← Back to all news
arXiv Machine Learning By Yutong Du, Zicheng Liu, Bo Qi, Yali Zong, Peixian Han

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

Read the original on arXiv Machine Learning →

The paper introduces a coordinate-residual physics-driven neural network (CRPDNN) for 3‑D electromagnetic inverse scattering. CRPDNN models the unknown contrast distribution using normalized spatial coordinates and a residual convolutional network, optimizing parameters by enforcing consistency between measured and predicted scattered fields. It eliminates the need for preliminary reconstruction, achieving lower relative error and significant speedups compared to existing methods, while maintaining stability under noisy measurements and showing promise in practical imaging experiments.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Oct 15

Structured Multi-Level-Set Inversion for 3-D Electromagnetic Inverse Scattering

The paper introduces Structured Multi-Level-Set Inversion (SMLSI), a physics‑driven neural network approach for 3‑D electromagnetic inverse scattering that represents contrast using object support and material distribution rather than direct parameterization. SMLSI employs multiple level‑sets mapped to soft‑support functions, a soft‑union operation, and trainable complex permittivities, with structure‑aware regularization to enforce binary support and coherent material regions. Numerical and experimental results show that SMLSI outperforms conventional methods like CSI and $L_{2/3}$‑FBE‑WCIE in reconstructing irregular geometries, closely spaced objects, and multiple material regions from scattered field data.

By Yutong Du, Zicheng Liu, Bo Qi, Yali Zong, Xin Li, Peixian Han
More like this →
arXiv AI
Aug 19

Inductively Scalable, Single-Step Neural Surrogates for Wave-Scattering Inverse Problems

The paper presents a method for training single‑step neural surrogates that can handle wave‑scattering problems with tens of thousands of controllable variables. By dynamically generating training examples that highlight surrogate errors and using a replay dataset with normalization, the authors achieve a surrogate that accurately simulates two‑dimensional wave scattering for up to 41,772 variables and generalizes to over 3 million variables without retraining. The surrogate is applied to forward simulations and inverse design of freeform beam splitters and gradient‑index lenses, achieving speedups up to 26.5× compared to traditional FDTD methods.

By Charles Dove, Laura Waller
More like this →
Hugging Face Trending Papers
Aug 18

Inductively Scalable, Single-Step Neural Surrogates for Wave-Scattering Inverse Problems

The paper presents a method for training single‑step neural surrogates that can handle wave‑scattering inverse problems with tens of thousands of controllable variables. By dynamically generating training examples through gradient ascent and using a replay dataset with normalization, the authors achieve a surrogate that accurately models two‑dimensional wave scattering for up to 41,772 variables and can generalize to over 3 million variables without retraining. The surrogate demonstrates comparable or better performance than traditional FDTD simulations for large‑scale forward simulations and inverse design of photonic devices, achieving speedups up to 26.5×.

More like this →