Eff-WRFGS: Efficient Wireless Radiance Field Using 3D Gaussian Splatting
摘要
Wireless channel modeling is a key building block for next-generation wireless systems. Predicting the channel state information (CSI) across different transmitter locations can substantially reduce the pilot and feedback overhead of conventional channel estimation. We propose Eff-WRFGS, an efficient wireless radiance field modeling framework built upon 3D Gaussian Splatting. Eff-WRFGS introduces a learnable mask for each 3D Gaussian primitive to indicate its importance, which guides the pruning of less significant primitives for more efficient rendering. The model is trained using a weighted combination of rendering and regularization losses, allowing a flexible trade-off between rendering quality and efficiency. Numerical results on the dataset demonstrate that Eff-WRFGS achieves up to 44 storage reduction and 7 rendering speed-up with only marginal quality degradation. Moreover, initializing the Gaussian primitives from a 3D point cloud of the scene further improves the entire quality-efficiency trade-off.
引用
@article{arxiv.2605.15324,
title = {Eff-WRFGS: Efficient Wireless Radiance Field Using 3D Gaussian Splatting},
author = {Chenghong Bian and Meng Hua and Deniz Gunduz},
journal= {arXiv preprint arXiv:2605.15324},
year = {2026}
}
备注
5 pages, for possible IEEE journal publication