用图注意力网络学习射频成像中的电磁场方程，实现快速高精度重建。
Graph-CNNs for RF Imaging: Learning the Electric Field Integral Equations
- 基于电磁场积分方程构建快速生成模型，支持数据驱动训练。
- 在两个合成数据集上实现优于传统方法的成像精度，抗噪声能力强。
- 适合需要低延迟、高鲁棒性的射频成像应用，如智能感知系统。
射频（RF）成像旨在通过分布式接收器捕获的散射场重建场景物体表面。针对这一复杂的逆散射问题，常采用数据驱动方法从相似样本中提取模式，具有低延迟优势。本文首先提出一种基于电场积分方程的快速近似电磁模型，用于高效生成训练数据；随后设计一种深度神经网络架构，学习对应逆问题映射。该模型采用图注意力骨干网络，将系统几何信息输入网络，残差卷积层提取物体特征，UNet解码器完成最终图像重建。在两个不同特性的合成数据集上的定量与定性评估表明，所提架构性能显著优于基准方法，且对信号噪声水平和多种接收配置具有较强鲁棒性。
原文摘要 · Abstract (English)
Radio-Frequency (RF) imaging concerns the digital recreation of the surfaces of scene objects based on the scattered field at distributed receivers. To solve this difficult inverse scattering problems, data-driven methods are often employed that extract patterns from similar training examples, while offering minimal latency. In this paper, we first provide an approximate yet fast electromagnetic model, which is based on the electric field integral equations, for data generation, and subsequently propose a Deep Neural Network (DNN) architecture to learn the corresponding inverse model. A graph-attention backbone allows for the system geometry to be passed to the DNN, where residual convolutional layers extract features about the objects, while a UNet head performs the final image reconstruction. Our quantitative and qualitative evaluations on two synthetic data sets of different characteristics showcase the performance gains of thee proposed advanced architecture and its relative resilience to signal noise levels and various reception configurations.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。