A Geometric Algebra-Informed 3DGS Framework for Wireless Channel Prediction

Jingzhou Shen; Tianya Zhao; Xuyu Wang

A Geometric Algebra-Informed 3DGS Framework for Wireless Channel Prediction

网络与互联网体系结构 2026-05-28 v2

作者: Jingzhou Shen , Tianya Zhao , Xuyu Wang

摘要

In this paper, we introduce Geometric Algebra-Informed 3D Gaussian Splatting (GAI-GS), a framework for wireless modeling that couples 3D Gaussian splatting with a geometric algebra-based attention mechanism to explicitly model ray-object interactions in complex propagation environments. GAI-GS encodes joint spatial-electromagnetic (EM) relations into token representations, enabling scene-level aggregation within a unified, end-to-end neural architecture. This design grounds wireless ray propagation in electromagnetic principles, allowing token interactions to model key effects such as multipath, attenuation, and reflection/diffraction. Through extensive evaluations on multiple real-world indoor datasets, GAI-GS consistently surpasses current baselines across various wireless tasks.

关键词

3d reconstruction

引用

@article{arxiv.2605.19065,
  title  = {A Geometric Algebra-Informed 3DGS Framework for Wireless Channel Prediction},
  author = {Jingzhou Shen and Tianya Zhao and Xuyu Wang},
  journal= {arXiv preprint arXiv:2605.19065},
  year   = {2026}
}