发表机构
Consiglio Nazionale delle Ricerche, IEIIT institute; Technical University of Munich (TUM)（意大利国家研究委员会，IEIIT研究所; 慕尼黑工业大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出W-LISTA和LoRaW-LISTA两种展开深度网络方法，用于EM信息全息成像，结合后在人体成像等任务中精度分辨率优于基线，且具备隐私保护特性。
AI 中文摘要
智能无线电环境（SRE）是万物互联（IoE）的基础范式，其中密集的相位相干天线阵列构成集成感知与通信（ISAC）的共享基础设施。射频（RF）全息术是SRE的核心感知组件，它从相位敏感的场测量中重建电磁（EM）散射场景的体积图，利用 stray RF辐射的基础设施快照，无需专用传感器。为使重建准确且快速适配，本文采用算法展开技术，将经典全息求解器的迭代过程转化为紧凑可训练深度网络的层，既保留EM物理解释，又仅从有限数据中学习少量参数。本文基于展开的迭代收缩阈值算法（ISTA），即学习型ISTA（LISTA），首先提出加权LISTA（W-LISTA），它保留EM正向模型并学习空间变化的正则化，将稀疏先验导向与部署一致的目标形状。其次，低秩加权LISTA（LoRaW-LISTA）对全息算子应用低秩适配（LoRa），以补偿线性化EM近似带来的模型失配。两种方法均通过全波EM仿真和2.45 GHz下含人体模型的室内实验验证，相比基线方法提升了精度和分辨率。将W-LISTA的空间变化正则化与EM模型的LoRa适配结合，可在经典迭代求解器失效时实现更优重建。所提工具是SRE感知层的快速适配组件，其重建结果（包括人体形状成像）天生具备隐私保护特性。
英文摘要
Radio-Frequency (RF) holographic imaging reconstructs a volumetric map of the permittivity contrast from phase-coherent samples of the scattered electromagnetic (EM) field. The resulting inverse problem is severely ill-posed, as the receivers are orders of magnitude fewer than the unknown 3D volume elements (voxels). It is classically regularized by sparsity-promoting solvers such as the Iterative Shrinkage-Thresholding Algorithm (ISTA). Two assumptions limit these solvers: the L1 penalty is spatially uniform, and the EM forward model is typically approximated as a linear operator. This paper revisits the problem through algorithm unrolling, in which the solver iterations become the layers of a compact trainable network that preserves the EM forward model and learns only a few interpretable parameters from limited data. Building on the Learned ISTA (LISTA), a Weighted LISTA (W-LISTA) is first proposed, which learns a spatially-varying L1 regularization, steering the sparsity prior towards target shapes consistent with the deployment. Second, the Low-Rank Weighted LISTA (LoRaW-LISTA) applies a low-rank adaptation (LoRa) of the holographic operator to compensate for model mismatches from linearized EM approximations. Both methods are validated on full-wave EM simulations and on a 2.45GHz indoor measurement campaign with human-body phantoms. Combining the spatially-varying regularization with the low-rank adaptation of the EM model improves the signal-to-clutter ratio by about 70% over the ISTA and LISTA baselines, recovering structural details where classical iterative solvers fail. Inference takes less than 30s to reconstruct 1m^3 of scene on conventional GPUs. The proposed tools are rapidly adaptable building blocks for the sensing layer of emerging smart radio environments.
Commentssubmitted for possible publication to IEEE
