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

2025-08-22

AI Summary

To address the high-throughput and high-accuracy spatial channel state information (Spatial-CSI) requirements of 6G, conventional channel modeling approaches face significant bottlenecks in spatial resolution, computational efficiency, and scalability; meanwhile, existing radiance field methods suffer from geometric distortion and prohibitively high supervision costs. This paper proposes a fully structured radio radiance field framework built upon planar Gaussian RF geometric primitives, integrated with multi-view supervision loss and a phased geometry–RF joint training strategy. By reconstructing dense propagation paths from sparse path-loss spectra, the method achieves surface-aligned, high-fidelity scene modeling. Experimental results demonstrate substantial improvements over state-of-the-art empirical models, ray-tracing methods, and mainstream radiance field approaches—particularly in modeling accuracy, training efficiency, and scene scalability.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

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.

Problem

• Reconstructs high-fidelity radio propagation paths from sparse data
• Improves geometric accuracy and reduces training costs for wireless channels
• Enables scalable spatial channel state information modeling for 6G

Innovation

• Planar Gaussians for geometry reconstruction
• Fully-structured radio radiance modeling
• Multi-view loss for RF propagation