Scalable 3D Gaussian Splatting-Based RF Signal Spatial Propagation Modeling

2025-02-03

AI Summary

To address the challenge of balancing high-fidelity RF propagation modeling with scalability in wireless network planning, this paper proposes RFSPM—a novel framework that introduces 3D Gaussian Splatting (3DGS) to RF signal spatial modeling for the first time. RFSPM features three key innovations: (1) Gaussian-parameterized RF scene representation, (2) gradient-guided learning of RF-specific attributes (e.g., path loss, multipath fading), and (3) RF-customized CUDA-accelerated ray tracing. The framework enables end-to-end differentiability and real-time, cross-band (RFID/BLE/LoRa/5G), multi-protocol RF signal prediction. Evaluated across four real-world deployments and two practical applications, RFSPM achieves fidelity comparable to state-of-the-art methods while reducing data requirements, training GPU-hours, and inference latency by 9.8×, 18.6×, and 84.4×, respectively. This substantial efficiency gain significantly enhances modeling scalability and deployment feasibility in large-scale wireless infrastructure design.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

Effective network planning and sensing in wireless networks require resource-intensive site surveys for data collection. An alternative is Radio-Frequency (RF) signal spatial propagation modeling, which computes received signals given transceiver positions in a scene (e.g.s a conference room). We identify a fundamental trade-off between scalability and fidelity in the state-of-the-art method. To address this issue, we explore leveraging 3D Gaussian Splatting (3DGS), an advanced technique for the image synthesis of 3D scenes in real-time from arbitrary camera poses. By integrating domain-specific insights, we design three components for adapting 3DGS to the RF domain, including Gaussian-based RF scene representation, gradient-guided RF attribute learning, and RF-customized CUDA for ray tracing. Building on them, we develop RFSPM, an end-to-end framework for scalable RF signal Spatial Propagation Modeling. We evaluate RFSPM in four field studies and two applications across RFID, BLE, LoRa, and 5G, covering diverse frequencies, antennas, signals, and scenes. The results show that RFSPM matches the fidelity of the state-of-the-art method while reducing data requirements, training GPU-hours, and inference latency by up to 9.8,$ imes$, 18.6,$ imes$, and 84.4,$ imes$, respectively.

Problem

• Scalable RF signal modeling
• 3D Gaussian Splatting adaptation
• Reduced data and computational needs

Innovation

• 3D Gaussian Splatting adaptation
• Gradient-guided RF learning
• Custom CUDA ray tracing