RINN: One Sample Radio Frequency Imaging based on Physics Informed Neural Network

2025-04-19

AI Summary

RF imaging under non-line-of-sight (NLOS) and low-light conditions suffers from low hardware precision, difficulty in phase acquisition, and scarcity of labeled training data. To address these challenges, this paper proposes a ground-truth-free physics-informed neural network (PINN) method. Leveraging Maxwell’s equations as hard physical priors, the approach requires only a single noisy amplitude-only measurement—eliminating dependence on phase information and multi-frame sampling. We formulate an amplitude-only forward physical model and incorporate adaptive noise-robust optimization to enable end-to-end high-fidelity reconstruction. Experiments demonstrate that our method achieves reconstruction quality comparable to five classical phase-based algorithms—even without phase measurements—achieving a relative root-mean-square error (RRMSE) as low as 0.11. By significantly reducing reliance on high-precision hardware and labeled datasets, our framework establishes a new paradigm for lightweight, low-cost RF vision systems.

Technology Category

• Computer Vision: Low Level & Physics-based Vision
• Intelligent Robots: State Estimation
• Search and Optimization: Non-convex Optimization

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Security and Privacy: Large-scale security measurements

Abstract

Due to its ability to work in non-line-of-sight and low-light environments, radio frequency (RF) imaging technology is expected to bring new possibilities for embodied intelligence and multimodal sensing. However, widely used RF devices (such as Wi-Fi) often struggle to provide high-precision electromagnetic measurements and large-scale datasets, hindering the application of RF imaging technology. In this paper, we combine the ideas of PINN to design the RINN network, using physical constraints instead of true value comparison constraints and adapting it with the characteristics of ubiquitous RF signals, allowing the RINN network to achieve RF imaging using only one sample without phase and with amplitude noise. Our numerical evaluation results show that compared with 5 classic algorithms based on phase data for imaging results, RINN's imaging results based on phaseless data are good, with indicators such as RRMSE (0.11) performing similarly well. RINN provides new possibilities for the universal development of radio frequency imaging technology.

Problem

• RF imaging lacks high-precision measurements and large datasets
• RINN enables RF imaging with single noisy amplitude-only sample
• RINN outperforms classic phase-based imaging algorithms

Innovation

• Physics Informed Neural Network for RF imaging
• Single sample imaging without phase data
• Robust to amplitude noise in RF signals