Point-Cloud-Assistant Localized Statistical Channel Prediction by Tangent Gaussian Splatting

2026-06-17

AI Summary

Existing local statistical channel modeling approaches struggle to predict the angular power spectrum (APS) in unmeasured regions, limiting their scalability. This work proposes a novel method that fuses sparse wireless measurements with dense LiDAR point clouds to model environmental scatterers as anisotropic 3D Gaussians via tangent-plane projection and depth-aware electromagnetic splatting, enabling the first point-cloud-assisted APS extrapolation. Key innovations include relaxed mean reparameterization for initialization, tangent-plane angular mapping, and a closed-form Gaussian-weighted average integral, accompanied by provable error bounds. Experiments on city-scale datasets demonstrate that the proposed approach substantially outperforms existing methods, achieving significant improvements in both APS and RSRP prediction accuracy as well as extrapolation inference speed.

Abstract

Accurate, site-specific channel information is crucial for optimizing next-generation wireless networks. Among various approaches, localized statistical channel modeling (LSCM), which models the channel multipath angular power spectrum (APS) from the reference signal received power (RSRP) measurement, has emerged as a state-of-the-art method tailored for efficient network optimization. However, despite its effectiveness, LSCM cannot predict APS at the vast majority of locations where no measurements are available, which significantly restricts its applicability in large-scale, real-world scenarios. To address this challenge, we present \emph{point-cloud-assisted tangent Gaussian splatting} (PC-TGS), the first framework to \emph{extrapolate} APS to unmeasured outdoor grids by integrating sparse radio measurements with dense LiDAR-based geometry. PC-TGS represents environmental scatterers as anisotropic 3D Gaussians, initialized and refined through a relaxed-mean reparameterization of the raw point cloud. A tangent-plane projection accurately maps each Gaussian into the local angular domain, while a depth-aware electromagnetic splatting process aggregates their contributions. To ensure practical deployment, we derive a closed-form Gaussian-weighted average (GWA) for APS bin integration and provide a provable error bound. { Evaluations on a LiDAR-scanned city-scale dataset (5M points, 6,310 RSRP samples) demonstrate that PC-TGS achieves better APS and RSRP prediction performance compared to state-of-the-art baselines and faster inference time for APS extrapolation task. These results highlight the potential of PC-TGS to enable geometry-aware and data-efficient channel prediction in large-scale wireless digital twins.

Problem

• localized statistical channel modeling
• angular power spectrum
• channel prediction
• extrapolation
• LiDAR

Innovation

• tangent Gaussian splatting
• localized statistical channel modeling
• point-cloud-assisted prediction
• angular power spectrum extrapolation
• geometry-aware channel prediction