Differentiable High-Performance Ray Tracing-Based Simulation of Radio Propagation with Point Clouds
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916828884762624 |
|---|---|
| author | Vaara, Niklas Sangi, Pekka López, Miguel Bordallo Heikkilä, Janne |
| author_facet | Vaara, Niklas Sangi, Pekka López, Miguel Bordallo Heikkilä, Janne |
| contents | Ray tracing is a widely used deterministic method for radio propagation simulations, capable of producing physically accurate multipath components. The accuracy depends on the quality of the environment model and its electromagnetic properties. Recent advances in computer vision and machine learning have made it possible to reconstruct detailed environment models augmented with semantic segmentation labels.
In this letter, we propose a differentiable ray tracing-based radio propagation simulator that operates directly on point clouds. We showcase the efficiency of our method by simulating multi-bounce propagation paths with up to five interactions with specular reflections and diffuse scattering in two indoor scenarios, each completing in less than 90 ms. Lastly, we demonstrate how the differentiability of electromagnetic computations can be combined with segmentation labels to learn the electromagnetic properties of the environment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_04021 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Differentiable High-Performance Ray Tracing-Based Simulation of Radio Propagation with Point Clouds Vaara, Niklas Sangi, Pekka López, Miguel Bordallo Heikkilä, Janne Signal Processing Computer Vision and Pattern Recognition Ray tracing is a widely used deterministic method for radio propagation simulations, capable of producing physically accurate multipath components. The accuracy depends on the quality of the environment model and its electromagnetic properties. Recent advances in computer vision and machine learning have made it possible to reconstruct detailed environment models augmented with semantic segmentation labels. In this letter, we propose a differentiable ray tracing-based radio propagation simulator that operates directly on point clouds. We showcase the efficiency of our method by simulating multi-bounce propagation paths with up to five interactions with specular reflections and diffuse scattering in two indoor scenarios, each completing in less than 90 ms. Lastly, we demonstrate how the differentiability of electromagnetic computations can be combined with segmentation labels to learn the electromagnetic properties of the environment. |
| title | Differentiable High-Performance Ray Tracing-Based Simulation of Radio Propagation with Point Clouds |
| topic | Signal Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.04021 |