Frequency-Aware Neural Radio-Frequency Radiance Fields

Although Maxwell discovered the physical laws of electromagnetic waves about 160 years ago, accurately modeling the propagation of RF signals in large and complex electrical environments remains a persistent challenge. This complexity arises from the interactions between the RF signal and various obstacles, including reflection and diffraction. Inspired by the success of neural networks in mapping the optical field in computer vision, we introduce the neural radio-frequency radiance field, or $\mathbf{NeRF}^{2}$. This represents a continuous volumetric scene function that effectively models RF signal propagation. Remarkably, after only a sparse amount of training with signal measurements, $\mathbf{NeRF}^{2}$ can accurately predict the nature and origin of signals received at any location, assuming the transmitter's position is known. Additionally, we propose the frequency-aware $\mathbf{NeRF}^{2}$ to enhance channel prediction performance for wideband signals using an RF prism module. Compared to the vanilla $\mathbf{NeRF}^{2}$, the frequency-aware $\mathbf{NeRF}^{2}$ achieves a 4 dB improvement in SNR for FDD OFDM channel estimation and is nearly 3.5 × faster. Functioning as a physical-layer neural network, $\mathbf{NeRF}^{2}$ also supports application-layer artificial neural networks (ANNs) by generating synthetic training datasets. Our empirical results demonstrate that augmented sensing enhances the accuracy of AoA estimation, achieving an approximate 50% improvement.