TGPP: Trajectory-Guided Plug-and-Play Priors for Sparse Radio Map Reconstruction

TL;DR

This paper introduces TGPP, a guidance module that improves sparse radio map reconstruction from trajectory-based measurements by learning explicit and implicit priors, enhancing accuracy across various models.

Contribution

The paper proposes TGPP, a versatile guidance module that can be integrated into different reconstruction models to effectively utilize trajectory-sampled data.

Findings

TGPP improves reconstruction metrics across multiple backbones.

Achieves up to 43.1% NMSE reduction with trajectory-guided priors.

Trajectory-sampled reconstruction significantly differs from random sparse interpolation.

Abstract

Radio map (RM) reconstruction is essential for environment-aware wireless networks, but practical measurements are often collected along mobility trajectories rather than randomly scattered over the target region. Such trajectory-sampled observations induce spatially heterogeneous uncertainty: near-trajectory regions are directly constrained, whereas distant or occluded regions remain weakly observed, leading to degraded reconstruction accuracy in under-constrained areas. To address this problem, we propose Trajectory-Guided Plug-and-Play Priors (TGPP), a general guidance module for sparse RM reconstruction. TGPP learns an explicit guidance map as an interpretable input-space risk prior, and an implicit guide feature that is projected and fused with backbone hidden representations. TGPP can be attached to different reconstruction backbones without changing their original task formulation. We further introduce RadioFlow-LDM, a latent flow-based generative backbone, and apply TGPP to deterministic, adversarial, graph-based, and latent generative reconstruction models. Experiments on RadioMapSeer with five trajectory sampling rates show that trajectory-sampled reconstruction differs substantially from random sparse interpolation. TGPP improves most reconstruction metrics across backbones, achieving up to 43.1% NMSE reduction relative to the corresponding base backbone without trajectory-guided priors.