RF-Diffusion: Radio Signal Generation via Time-Frequency Diffusion

TL;DR

RF-Diffusion introduces a diffusion-based framework tailored to RF signals by coupling Time-Frequency Diffusion (TFD) with a Hierarchical Diffusion Transformer (HDT). The core idea is to destruct and restore RF data through simultaneous time-domain noise and frequency-domain blur, enabling high-fidelity, time-series RF generation that preserves spectral details and complex-valued information. The approach supports conditional generation, complex-valued processing, and phase-aware encoding, achieving state-of-the-art fidelity (SSIM around 0.81 for Wi‑Fi and 0.75 for FMCW) and strong improvements in downstream tasks such as Wi‑Fi gesture recognition and 5G FDD channel estimation. The work provides extensive experiments on Wi‑Fi and FMCW data, demonstrates data augmentation benefits, and offers public code to encourage adoption and further research in RF-aware AIGC.

Abstract

Along with AIGC shines in CV and NLP, its potential in the wireless domain has also emerged in recent years. Yet, existing RF-oriented generative solutions are ill-suited for generating high-quality, time-series RF data due to limited representation capabilities. In this work, inspired by the stellar achievements of the diffusion model in CV and NLP, we adapt it to the RF domain and propose RF-Diffusion. To accommodate the unique characteristics of RF signals, we first introduce a novel Time-Frequency Diffusion theory to enhance the original diffusion model, enabling it to tap into the information within the time, frequency, and complex-valued domains of RF signals. On this basis, we propose a Hierarchical Diffusion Transformer to translate the theory into a practical generative DNN through elaborated design spanning network architecture, functional block, and complex-valued operator, making RF-Diffusion a versatile solution to generate diverse, high-quality, and time-series RF data. Performance comparison with three prevalent generative models demonstrates the RF-Diffusion's superior performance in synthesizing Wi-Fi and FMCW signals. We also showcase the versatility of RF-Diffusion in boosting Wi-Fi sensing systems and performing channel estimation in 5G networks.

Figures (13)

• Figure 1: RF-Diffusion overview.
• Figure 2: Illustration of the conditional forward and reverse trajectories.
• Figure 3: Hierarchical Diffusion Transformer design.
• Figure 4: Illustration of phase modulation encoding.
• Figure 5: Experimental scenarios.