# Radio Frequency Ray Tracing with Neural Object Representation

arXiv: https://arxiv.org/abs/2411.18635 · HTML: https://mlsanity.com/paper/2411.18635/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Nov 2024.

## Built on by (most cited first, 10 of 10)

- [Generalizable Radio-Frequency Radiance Fields for Spatial Spectrum Synthesis](https://mlsanity.com/paper/2502.05708/) (2025)
- [Scalable RF Simulation in Generative 4D Worlds](https://mlsanity.com/paper/2508.12176/) (2025)
- [Physically Accurate Differentiable Inverse Rendering for Radio Frequency Digital Twin](https://mlsanity.com/paper/2603.18026/) (2026)
- [Point2Radio: A Foundation Model for Cross-Scene Radio Fields from Material-Aware Point Clouds](https://mlsanity.com/paper/2607.28994/) (2026)
- [Transform-Invariant Generative Ray Path Sampling for Efficient Radio Propagation Modeling](https://mlsanity.com/paper/2603.01655/) (2026)
- [Neural Electromagnetic Fields for High-Resolution Material Parameter Reconstruction](https://mlsanity.com/paper/2603.02582/) (2026)
- [GeRaF: Neural Geometry Reconstruction from Radio Frequency Signals](https://mlsanity.com/paper/2605.29097/) (2026)
- [HybridSim: A Physics-Learning Hybrid Digital Twin for mmWave Human Sensing](https://mlsanity.com/paper/2607.15806/) (2026)
- [Physics-Unrolled Neural Operator for Wireless Field Modeling](https://mlsanity.com/paper/2608.18495/) (2026)
- [RFWeave: Learning Wireless Propagation Across Scenes and Transceiver Configurations](https://mlsanity.com/paper/2610.16656/) (2026)

## Abstract (arXiv)

Radio frequency (RF) propagation modeling poses unique electromagnetic simulation challenges. While recent neural representations have shown success in visible spectrum rendering, the fundamentally different scales and physics of RF signals require novel modeling paradigms. In this paper, we introduce RFScape, a novel framework that bridges the gap between neural scene representation and RF propagation modeling. Our key insight is that complex RF-object interactions can be captured through object-centric neural representations while preserving the composability of traditional ray tracing. Unlike previous approaches that either rely on crude geometric approximations or require dense spatial sampling of entire scenes, RFScape learns per-object electromagnetic properties and enables flexible scene composition. Through extensive evaluation on real-world RF testbeds, we demonstrate that our approach achieves 13 dB improvement over conventional ray tracing and 5 dB over state-of-the-art neural baselines in modeling accuracy while requiring only sparse training samples.