文章背景与核心概要

GSBF（Gaussian Splatting for Environment-Aware Beamforming）是一项针对多输入多输出（MIMO）通信系统的创新性研究。该技术核心在于认识到无线电传播本质上受物理几何结构的制约，因此利用多模态数据和持久化的 3D 高斯表示来精确刻画通信环境。

该方法通过互易性保持的双向球形高斯（Bi-SG）核来建模环境散射响应，并利用双向电磁光栅化技术渲染角度传播图。这种方法成功摆脱了对在线瞬时信道状态信息（CSI）和迭代优化的依赖，能够直接根据接入点（AP）姿态和用户位置合成波束，在降低延迟的同时，性能显著优于穷举波束对齐（EBA）等传统基准方案。

GSBF：面向环境感知波束赋形的 3D 高斯溅射技术

摘要

GSBF (Gaussian Splatting for Environment-Aware Beamforming) is an innovative pipeline designed for multiple-input-multiple-output (MIMO) communication systems. By recognizing that radio propagation is fundamentally governed by physical geometry, GSBF uses multi-modal data and a persistent 3D Gaussian representation to characterize the environment. It models environmental scattering with reciprocity-preserving bidirectional spherical Gaussian (Bi-SG) kernels and renders an angular propagator map through two-sided electromagnetic rasterization. This approach eliminates the need for online instantaneous channel state information (CSI) and iterative optimization, successfully synthesizing beams directly from access point (AP) poses and user positions with reduced latency and superior performance compared to traditional baselines like exhaustive beam alignment (EBA).

波束赋形在多输入多输出（MIMO）通信系统中起着关键作用。然而，传统的波束赋形设计通常需要精确的瞬时信道状态信息（CSI）和迭代优化，这会带来巨大的导频开销和计算复杂度。基于无线电传播本质上受物理几何结构支配的认识，我们开发了一种基于多模态数据的 3D 高斯溅射环境感知波束赋形（GSBF）流水线，通过持久的 3D 高斯表示来刻画环境。具体而言，GSBF 使用互易性保持的双向球形高斯（Bi-SG）核对环境散射响应进行建模，并执行双向电磁光栅化以渲染角度传播图。随后，渲染出的地图通过过完备阵列流形字典进行聚合，并投影到恒模波束赋形器上，从而在无需在线瞬时 CSI 的情况下，直接根据接入点（AP）姿态和用户位置合成波束。仿真结果表明，GSBF 在保持较低延迟的同时，性能始终优于穷举波束对齐（EBA）等基准方案。

Abstract Beamforming plays a key role in multiple-input-multiple-output (MIMO) communication systems. However, conventional beamforming design normally requires accurate instantaneous channel state information (CSI) and iterative optimization, which incur substantial pilot overhead and computational complexity. Recognizing that radio propagation is intrinsically governed by the physical geometry, we develop a 3D Gaussian splatting for environment-aware beamforming (GSBF) pipeline based on multi-modal data, which characterizes the environment through a persistent 3D Gaussian representation. Specifically, GSBF models the environmental scattering response with reciprocity-preserving bidirectional spherical Gaussian (Bi-SG) kernels and performs two-sided electromagnetic rasterization to render an angular propagator map. The rendered map is then aggregated through an over-complete array-manifold dictionary and projected to the constant-modulus beamformers, thereby synthesizing beams directly from the access point (AP) pose and user position without online instantaneous CSI. Simulations demonstrate that GSBF consistently outperforms baselines such as exhaustive beam alignment (EBA) with lower latency.

元数据与文档信息

作者

• Yijie Bian
• Wei Guo
• Zixin Wang
• Shenghui Song
• Jun Zhang
• Khaled B. Letaief

访问与资源

• 全文链接：
• 查看 PDF
• HTML 版本 (实验性)
• TeX 源码
• 外部引用与工具：
• Google Scholar
• Semantic Scholar
• NASA ADS