Reconstructing 3D Radiance Field (RF) scenes through opaque obstacles is a long-standing goal, yet it is fundamentally constrained by a laborious data acquisition process requiring thousands of static measurements, which treats human motion as noise to be filtered. This work introduces a new paradigm with a core objective: to perform fast, data-efficient, and high-fidelity RF reconstruction of occluded 3D static scenes, using only a single, brief human walk. We argue that this unstructured motion is not noise, but is in fact an information-rich signal available for reconstruction. To achieve this, we design a factorization framework based on composite 3D Gaussian Splatting (3DGS) that learns to model the dynamic effects of human motion from the persistent static scene geometry within a raw RF stream. Trained on just a single 60-second casual walk, our model reconstructs the full static scene with a Structural Similarity Index (SSIM) of 0.96, remarkably outperforming heavily-sampled state-of-the-art (SOTA) by 12%. By transforming the human movements into its valuable signals, our method eliminates the data acquisition bottleneck and paves the way for on-the-fly 3D RF mapping of unseen environments.
@article{arxiv.2511.16966,
title = {One Walk is All You Need: Data-Efficient 3D RF Scene Reconstruction with Human Movements},
author = {Yiheng Bian and Zechen Li and Lanqing Yang and Hao Pan and Yezhou Wang and Longyuan Ge and Jeffery Wu and Ruiheng Liu and Yongjian Fu and Yichao chen and Guangtao xue},
journal= {arXiv preprint arXiv:2511.16966},
year = {2025}
}