arXiv：cs.LG· Yutong Du, Zicheng Liu, Bo Qi, Yali Zong, Xin Li, Peixian Han·· 4 小时前
SMLSI：面向3-D电磁逆散射的结构化多水平集反演方法
Structured Multi-Level-Set Inversion for 3-D Electromagnetic Inverse Scattering
AI 导读
针对3-D电磁逆散射中分段均匀介质目标，研究者提出结构化多水平集反演（SMLSI）方法，在物理驱动神经网络（PDNN）框架下用物体支撑与材料分布表示对比度。该方法通过软并集组合多个水平集构建支撑，结合可训练复相对介电常数确定材料分布，并引入结构感知正则化与自适应权重。
正文
Abstract:Many dielectric targets encountered in 3-D electromagnetic inverse scattering exhibit piecewise-homogeneous material distributions, which provide useful structural information for inversion. To exploit this property, this paper proposes a structured multi-level-set inversion (SMLSI) method within a physics-driven neural network (PDNN) framework. Instead of directly parameterizing the contrast distribution, SMLSI represents it in terms of object support and material distribution. Multiple level-sets are mapped to soft-support functions and combined through a soft-union operation to construct the object support. The normalized contributions of these soft-support functions, together with trainable complex relative permittivities, determine the material distribution within the support. The level-set residuals are parameterized by a coordinate-based neural network, and the trainable parameters are optimized from scattered field data. Structure-aware regularization terms are introduced to promote binary object support and spatially coherent material regions while reducing material mixing and redundant activation of level-set supports. Adaptive regularization weighting is further employed to reduce the dependence on manual parameter tuning. Numerical experiments demonstrate that SMLSI improves reconstruction accuracy over direct contrast parameterization and enables the recovery of irregular 3-D geometries, closely spaced objects, and multiple material regions. Compared with CSI and $L_{2/3}$-FBE-WCIE, SMLSI achieves more accurate reconstructions on representative synthetic targets. Experimental validation using 3-D Fresnel data further demonstrates its applicability to measured scattering data.
| Subjects: | Machine Learning (cs.LG); Computational Physics (physics.comp-ph) |
| Cite as: | arXiv:2609.08594 [cs.LG] |
| (or arXiv:2609.08594v3 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2609.08594 arXiv-issued DOI via DataCite |
Submission history
From: Yutong Du [view email]
[v1]
Tue, 8 Sep 2026 11:30:32 UTC (20,423 KB)
[v2]
Sat, 10 Oct 2026 04:13:25 UTC (17,911 KB)
[v3]
Wed, 14 Oct 2026 06:54:42 UTC (17,911 KB)
来源：arXiv：cs.LG · arxiv.org