ScoreField：基于得分生成先验的神经逆散射方法
ScoreField: Neural Inverse Scattering with Score-Based Generative Priors
- Johns Hopkins University（约翰斯·霍普金斯大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
ScoreField是结合耦合隐式神经表示与预训练得分生成先验的神经逆散射框架，可处理强多次散射，在多类基准及实验数据上的重建性能优于经典全波方法与深度学习基线。
AI中文摘要：
设计有效的电磁逆散射求解器，需要同时严格满足非线性全波物理约束，并对未知的介电常数对比度施加具有表达能力的先验。我们提出ScoreField，这是一种神经逆散射框架，将耦合的隐式神经表示（INRs）与预训练的基于得分的生成先验相结合。ScoreField使用两个INRs分别参数化介电常数对比度和感应电流场，并在Lippmann-Schwinger方程下对它们进行联合优化。除了INRs架构带来的隐式正则化外，得分模型还提供了关于对比度的学习先验梯度，该梯度通过链式法则传播到对比度INR。该公式使ScoreField能够有效处理强多次散射，其中非线性波相互作用需要对耦合的全波物理进行精确建模。我们在模拟的弱散射和强散射基准、标准Austria体模以及实验性Fresnel测量数据上评估ScoreField。结果表明，与经典全波方法和深度学习基线相比，ScoreField显著提高了重建保真度并抑制了伪影，在真实Fresnel数据上，其相较于最优竞争方法的平均峰值信噪比（PSNR）提升达到1.8 dB。
英文摘要：
Designing an effective electromagnetic inverse-scattering solver requires faithful enforcement of nonlinear full-wave physics together with an expressive prior on the unknown permittivity contrast. We propose ScoreField, a neural inverse scattering framework that integrates coupled implicit neural representations (INRs) with a pretrained score-based generative prior. ScoreField employs two INRs to parameterize the permittivity contrast and the induced current fields, and jointly optimize them under the Lippmann-Schwinger equations. In addition to the implicit regularization by the INR architecture, the score model provides a learned prior gradient on the contrast, which is propagated to the contrast INR through the chain rule. This formulation enables ScoreField to effectively handle strong multiple scattering, where nonlinear wave interactions require accurate modeling of the coupled full-wave physics. We evaluate ScoreField on simulated weak- and strong-scattering benchmarks, the canonical Austria phantom, and experimental Fresnel measurements. We note that ScoreField significantly improves reconstruction fidelity and suppresses artifacts relative to classical full-wave methods and deep learning baselines, achieving an average PSNR improvement of $1.8 \, \mathrm{dB}$ over the best competing method on real Fresnel data.
