Scalable RF Simulation in Generative 4D Worlds

Zhiwei Zheng, Dongyin Hu, Mingmin Zhao

Keywords: Simulation, Millimeter Wave Sensing, Generalization, Large Language Model, Human Motion Generation

Abstract: Radio Frequency (RF) sensing has emerged as a powerful, privacy-preserving alternative to vision-based methods for various perception tasks. However, building high-quality RF datasets in dynamic and diverse environments remains a major challenge. To address this, we introduce WaveVerse, a prompt-based, scalable framework that simulates realistic RF signals from generated indoor scenes with human motions. WaveVerse introduces a language-guided 4D world generator and a physics-based signal simulator that enables the realistic simulation of RF signals in diverse environments. Experiments validate the effectiveness of our method, and we present two case studies showing WaveVerse not only enables data generation for RF imaging for the first time, but also consistently achieves performance gains in both data-limited and data-adequate scenarios.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 3562