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

2025-05-27

AI Summary

Existing methods for modeling broadband radio-frequency (RF) radiation fields are limited to single-frequency modeling, failing to generalize across wide bandwidths (1–100 GHz). Method: This paper proposes Frequency-Embedded 3D Gaussian Splatting (F-3DGS), the first framework to explicitly incorporate electromagnetic wave propagation physics into 3D Gaussian Splatting (3DGS). It introduces a dual-module electromagnetic feature network—comprising attenuation and radiation subnetworks—to enable end-to-end differentiable rendering and joint modeling of power-angle spectra (PAS) across broadband frequencies. Contribution/Results: F-3DGS achieves zero-shot frequency generalization, overcoming the single-frequency bottleneck. Evaluated on a proprietary 50,000-sample PAS dataset, it attains an SSIM of 0.72—outperforming the state-of-the-art by 17.8%. For unseen frequencies under zero-shot inference, SSIM remains at 0.70 (only a 2.8% drop), demonstrating both high modeling accuracy and strong cross-frequency generalization capability.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: 3D Computer Vision
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

This paper presents an innovative frequency-embedded 3D Gaussian splatting (3DGS) algorithm for wideband radio-frequency (RF) radiance field modeling, offering an advancement over the existing works limited to single-frequency modeling. Grounded in fundamental physics, we uncover the complex relationship between EM wave propagation behaviors and RF frequencies. Inspired by this, we design an EM feature network with attenuation and radiance modules to learn the complex relationships between RF frequencies and the key properties of each 3D Gaussian, specifically the attenuation factor and RF signal intensity. By training the frequency-embedded 3DGS model, we can efficiently reconstruct RF radiance fields at arbitrary unknown frequencies within a given 3D environment. Finally, we propose a large-scale power angular spectrum (PAS) dataset containing 50000 samples ranging from 1 to 100 GHz in 6 indoor environments, and conduct extensive experiments to verify the effectiveness of our method. Our approach achieves an average Structural Similarity Index Measure (SSIM) up to 0.72, and a significant improvement up to 17.8% compared to the current state-of-the-art (SOTA) methods trained on individual test frequencies. Additionally, our method achieves an SSIM of 0.70 without prior training on these frequencies, which represents only a 2.8% performance drop compared to models trained with full PAS data. This demonstrates our model's capability to estimate PAS at unknown frequencies. For related code and datasets, please refer to https://github.com/sim-2-real/Wideband3DGS.

Problem

• Modeling wideband RF radiance fields using frequency-embedded 3D Gaussian splatting
• Learning complex relationships between RF frequencies and 3D Gaussian properties
• Reconstructing RF radiance fields at arbitrary unknown frequencies efficiently

Innovation

• Frequency-embedded 3D Gaussian splatting algorithm
• EM feature network with attenuation modules
• Large-scale power angular spectrum dataset