Wideband RF Radiance Field Modeling Using Frequency-embedded 3D Gaussian Splatting

TL;DR

This work tackles the problem of wideband RF radiance-field modeling in indoor environments by introducing a frequency-embedded 3D Gaussian Splatting framework. The method combines a frequency-aware EM feature network with a differentiable 3DGS PAS renderer to predict the Power Angular Spectrum across arbitrary TX positions and frequencies within a given scene, using limited multi-frequency data. Through a large-scale simulated PAS dataset spanning $1$ to $94$ GHz, the approach achieves a $6.8\%$ improvement in PAS reconstruction SSIM over single-frequency state-of-the-art methods and demonstrates robust cross-frequency generalization and zero-/few-shot extrapolation to unseen frequencies. The results suggest that embedding frequency information directly into the Gaussian attributes enables accurate wideband RF propagation modeling, with practical implications for heterogeneous RF systems, spectrum sensing, and RF localization.

Abstract

Indoor environments typically contain diverse RF signals distributed across multiple frequency bands, including NB-IoT, Wi-Fi, and millimeter-wave. Consequently, wideband RF modeling is essential for practical applications such as joint deployment of heterogeneous RF systems, cross-band communication, and distributed RF sensing. Although 3D Gaussian Splatting (3DGS) techniques effectively reconstruct RF radiance fields at a single frequency, they cannot model fields at arbitrary or unknown frequencies across a wide range. In this paper, we present a novel 3DGS algorithm for unified wideband RF radiance field modeling. RF wave propagation depends on signal frequency and the 3D spatial environment, including geometry and material electromagnetic (EM) properties. To address these factors, we introduce a frequency-embedded EM feature network that utilizes 3D Gaussian spheres at each spatial location to learn the relationship between frequency and transmission characteristics, such as attenuation and radiance intensity. With a dataset containing sparse frequency samples in a specific 3D environment, our model can efficiently reconstruct RF radiance fields at arbitrary and unseen frequencies. To assess our approach, we introduce a large-scale power angular spectrum (PAS) dataset with 50,000 samples spanning 1 to 94 GHz across six indoor environments. Experimental results show that the proposed model trained on multiple frequencies achieves a Structural Similarity Index Measure (SSIM) of 0.922 for PAS reconstruction, surpassing state-of-the-art single-frequency 3DGS models with SSIM of 0.863.

Figures (6)

• Figure 1: EM waves exhibit complex propagation behaviors that are closely influenced by factors such as materials, wavelengths, and the shapes of obstacles.
• Figure 2: An example of the power angular spectrum.
• Figure 3: Architecture of the frequency embedding-based 3D Gaussian Splatting model.
• Figure 4: Example of PAS reconstruction at diverse frequencies.
• Figure 5: The 6 scenes used for dataset generation and experiments. The blue circular mark indicates the position of RX.