One Walk is All You Need: Data-Efficient 3D RF Scene Reconstruction with Human Movements

TL;DR

This paper presents a novel method for rapid, data-efficient 3D scene reconstruction using only a single human walk, leveraging human motion as a valuable signal rather than noise, and significantly reducing data requirements.

Contribution

It introduces a factorization framework based on 3D Gaussian Splatting that models dynamic human motion from static scene geometry, enabling high-fidelity reconstruction from minimal data.

Findings

Reconstructed scenes achieve SSIM of 0.96

Outperforms state-of-the-art methods by 12%

Requires only a 60-second casual walk for training

Abstract

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.