RadioDiff-FS: Physics-Informed Manifold Alignment in Few-Shot Diffusion Models for High-Fidelity Radio Map Construction

TL;DR

RadioDiff-FS introduces a physics-informed, few-shot diffusion framework for high-fidelity radio map construction, effectively adapting to complex environments with minimal data by leveraging a theoretical decomposition and directional constraints.

Contribution

The paper presents a novel physics-informed diffusion model that enables effective few-shot adaptation for radio map construction, addressing data scarcity and complex multipath environments.

Findings

Reduces NMSE by 59.5% on static RMs

Achieves SSIM of 0.9752 and PSNR of 36.37 dB

Outperforms fully supervised baselines in one-shot scenarios

Abstract

Radio maps (RMs) provide spatially continuous propagation characterizations essential for 6G network planning, but high-fidelity RM construction remains challenging. Rigorous electromagnetic solvers incur prohibitive computational latency, while data-driven models demand massive labeled datasets and generalize poorly from simplified simulations to complex multipath environments. This paper proposes RadioDiff-FS, a few-shot diffusion framework that adapts a pretrained main-path generator to multipath-rich target domains with only a small number of high-fidelity samples. The adaptation is grounded in a theoretical decomposition of the multipath RM into a dominant main-path component and a directionally sparse residual. This decomposition shows that the cross-domain shift corresponds to a bounded and geometrically structured feature translation rather than an arbitrary distribution change. A direction-consistency loss (DCL) is then introduced to constrain diffusion score updates along physically plausible propagation directions, thereby suppressing phase-inconsistent artifacts that arise in the low-data regime. Experiments show that RadioDiff-FS reduces NMSE by 59.5\% on static RMs and by 74.0\% on dynamic RMs relative to the vanilla diffusion baseline, achieving an SSIM of 0.9752 and a PSNR of 36.37 dB under severely limited supervision. Even in a one-shot setting with a single target-domain sample per scene, RadioDiff-FS outperforms all fully supervised baselines, confirming that the directional constraint provides an effective inductive bias under extreme data scarcity. Code is available at https://github.com/UNIC-Lab/RadioDiff-FS.