RF-PGS: Fully-structured Spatial Wireless Channel Representation with Planar Gaussian Splatting

TL;DR

RF-PGS introduces a novel, efficient framework for high-fidelity spatial wireless channel modeling using planar Gaussian splatting, addressing limitations of traditional methods in 6G applications.

Contribution

It proposes a fully-structured, geometry-aware radiance field approach with RF-specific optimizations for scalable 6G Spatial-CSI reconstruction from sparse data.

Findings

Achieves dense, surface-aligned scene reconstruction.

Significantly improves reconstruction accuracy over prior methods.

Reduces training costs and enhances efficiency.

Abstract

In the 6G era, the demand for higher system throughput and the implementation of emerging 6G technologies require large-scale antenna arrays and accurate spatial channel state information (Spatial-CSI). Traditional channel modeling approaches, such as empirical models, ray tracing, and measurement-based methods, face challenges in spatial resolution, efficiency, and scalability. Radiance field-based methods have emerged as promising alternatives but still suffer from geometric inaccuracy and costly supervision. This paper proposes RF-PGS, a novel framework that reconstructs high-fidelity radio propagation paths from only sparse path loss spectra. By introducing Planar Gaussians as geometry primitives with certain RF-specific optimizations, RF-PGS achieves dense, surface-aligned scene reconstruction in the first geometry training stage. In the subsequent Radio Frequency (RF) training stage, the proposed fully-structured radio radiance, combined with a tailored multi-view loss, accurately models radio propagation behavior. Compared to prior radiance field methods, RF-PGS significantly improves reconstruction accuracy, reduces training costs, and enables efficient representation of wireless channels, offering a practical solution for scalable 6G Spatial-CSI modeling.