PointNeRT: A Physics Aware Neural Ray Tracing Surrogate for Propagation Channel Modeling

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Zhuoyin, He, Ruisi, Yang, Mi, Qi, Ziyi, Zhang, Zhengyu, Han, Jiahui, Zhang, Haoxiang, Liu, Bingcheng
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913116466446336
author Li, Zhuoyin
He, Ruisi
Yang, Mi
Qi, Ziyi
Zhang, Zhengyu
Han, Jiahui
Zhang, Haoxiang
Liu, Bingcheng
author_facet Li, Zhuoyin
He, Ruisi
Yang, Mi
Qi, Ziyi
Zhang, Zhengyu
Han, Jiahui
Zhang, Haoxiang
Liu, Bingcheng
contents Ray tracing (RT) has emerged as a key tool for propagation channel modeling and network planning. Conventional RT is based on electromagnetic (EM) wave theory and its application relies on detailed mesh-based environment representations and material properties. In realistic environments, limited environmental geometry and material uncertainties hinder its scalability to complex scenarios. In this paper, we propose a novel physics aware neural RT surrogate named PointNeRT to address these limitations. The proposed model directly takes point clouds as environmental input, and efficiently reconstruct multipath without explicitly constructing mesh models or manually defining EM interaction rules. PointNeRT adopts a hop-by-hop modeling strategy guided by physical interaction constraints. It supports sequential prediction of multipath propagation and power attenuation. Numerical results and experiments demonstrate that the proposed method implicitly captures surface normal characteristics and EM material effects. It further achieves robust generalization in mobility scenarios and provides a physics-guided neural modeling of multipath propagation.
format Preprint
id arxiv_https___arxiv_org_abs_2605_11828
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PointNeRT: A Physics Aware Neural Ray Tracing Surrogate for Propagation Channel Modeling
Li, Zhuoyin
He, Ruisi
Yang, Mi
Qi, Ziyi
Zhang, Zhengyu
Han, Jiahui
Zhang, Haoxiang
Liu, Bingcheng
Signal Processing
Ray tracing (RT) has emerged as a key tool for propagation channel modeling and network planning. Conventional RT is based on electromagnetic (EM) wave theory and its application relies on detailed mesh-based environment representations and material properties. In realistic environments, limited environmental geometry and material uncertainties hinder its scalability to complex scenarios. In this paper, we propose a novel physics aware neural RT surrogate named PointNeRT to address these limitations. The proposed model directly takes point clouds as environmental input, and efficiently reconstruct multipath without explicitly constructing mesh models or manually defining EM interaction rules. PointNeRT adopts a hop-by-hop modeling strategy guided by physical interaction constraints. It supports sequential prediction of multipath propagation and power attenuation. Numerical results and experiments demonstrate that the proposed method implicitly captures surface normal characteristics and EM material effects. It further achieves robust generalization in mobility scenarios and provides a physics-guided neural modeling of multipath propagation.
title PointNeRT: A Physics Aware Neural Ray Tracing Surrogate for Propagation Channel Modeling
topic Signal Processing
url https://arxiv.org/abs/2605.11828