Saved in:
Bibliographic Details
Main Authors: Bian, Kejia, Tao, Meixia, Sun, Shu, Yu, Jun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.18295
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908416808583168
author Bian, Kejia
Tao, Meixia
Sun, Shu
Yu, Jun
author_facet Bian, Kejia
Tao, Meixia
Sun, Shu
Yu, Jun
contents Neural ray tracing (RT) has emerged as a promising paradigm for channel modeling by combining physical propagation principles with neural networks. It enables high modeling accuracy and efficiency. However, current neural RT methods face two key limitations: constrained generalization capability due to strong spatial dependence, and weak adherence to electromagnetic laws. In this paper, we propose GeNeRT, a Generalizable Neural RT framework with enhanced generalization, accuracy and efficiency. GeNeRT supports both intra-scenario spatial transferability and inter-scenario zero-shot generalization. By incorporating Fresnel-inspired neural network design, it also achieves higher accuracy in multipath component (MPC) prediction. Furthermore, a GPU-tensorized acceleration strategy is introduced to improve runtime efficiency. Extensive experiments conducted in outdoor scenarios demonstrate that GeNeRT generalizes well across untrained regions within a scenario and entirely unseen environments, and achieves superior accuracy in MPC prediction compared to baselines. Moreover, it outperforms Wireless Insite in runtime efficiency, particularly in multi-transmitter settings. Ablation experiments validate the effectiveness of the network architecture and training strategy in capturing physical principles of ray-surface interactions.
format Preprint
id arxiv_https___arxiv_org_abs_2506_18295
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GeNeRT: A Physics-Informed Approach to Intelligent Wireless Channel Modeling via Generalizable Neural Ray Tracing
Bian, Kejia
Tao, Meixia
Sun, Shu
Yu, Jun
Machine Learning
Artificial Intelligence
Neural ray tracing (RT) has emerged as a promising paradigm for channel modeling by combining physical propagation principles with neural networks. It enables high modeling accuracy and efficiency. However, current neural RT methods face two key limitations: constrained generalization capability due to strong spatial dependence, and weak adherence to electromagnetic laws. In this paper, we propose GeNeRT, a Generalizable Neural RT framework with enhanced generalization, accuracy and efficiency. GeNeRT supports both intra-scenario spatial transferability and inter-scenario zero-shot generalization. By incorporating Fresnel-inspired neural network design, it also achieves higher accuracy in multipath component (MPC) prediction. Furthermore, a GPU-tensorized acceleration strategy is introduced to improve runtime efficiency. Extensive experiments conducted in outdoor scenarios demonstrate that GeNeRT generalizes well across untrained regions within a scenario and entirely unseen environments, and achieves superior accuracy in MPC prediction compared to baselines. Moreover, it outperforms Wireless Insite in runtime efficiency, particularly in multi-transmitter settings. Ablation experiments validate the effectiveness of the network architecture and training strategy in capturing physical principles of ray-surface interactions.
title GeNeRT: A Physics-Informed Approach to Intelligent Wireless Channel Modeling via Generalizable Neural Ray Tracing
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2506.18295