# FM-RME: Foundation Model Empowered Radio Map Estimation

arXiv: https://arxiv.org/abs/2602.22231 · HTML: https://mlsanity.com/paper/2602.22231/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 20 references that are in the map.
- First posted on arXiv 15 Feb 2026.

## Builds on (most cited first, 7 of 7)

- [RadioUNet: Fast Radio Map Estimation with Convolutional Neural Networks](https://mlsanity.com/paper/1911.09002/) (2019)
- [Deep Completion Autoencoders for Radio Map Estimation](https://mlsanity.com/paper/2005.05964/) (2020)
- [Radio Map Estimation: A Data-Driven Approach to Spectrum Cartography](https://mlsanity.com/paper/2202.03269/) (2022)
- [Spatial Transformers for Radio Map Estimation](https://mlsanity.com/paper/2411.01211/) (2024)
- [Distributed Swarm Learning for Edge Internet of Things](https://mlsanity.com/paper/2403.20188/) (2024)
- [Physics-Inspired Distributed Radio Map Estimation](https://mlsanity.com/paper/2502.00319/) (2025)
- [Temporal Spectrum Cartography in Low-Altitude Economy Networks: A Generative AI Framework with Multi-Agent Learning](https://mlsanity.com/paper/2505.15571/) (2025)

## Built on by (most cited first, 1 of 1)

- [Wireless Foundation Models: State-of-the-Art and Open Challenges](https://mlsanity.com/paper/2609.04707/) (2026)

## Abstract (arXiv)

Traditional radio map estimation (RME) techniques fail to capture multi-dimensional and dynamic characteristics of complex spectrum environments. Recent data-driven methods achieve accurate RME in spatial domain, but ignore physical prior knowledge of radio propagation, limiting data efficiency especially in multi-dimensional scenarios. To overcome such limitations, we propose a new foundation model, characterized by self-supervised pre-training on diverse data for zero-shot generalization, enabling multi-dimensional radio map estimation (FM-RME). Specifically, FM-RME builds an effective synergy of two core components: a geometry-aware feature extraction module that encodes physical propagation symmetries, i.e., translation and rotation invariance, as inductive bias, and an attention-based neural network that learns long-range correlations across the spatial-temporal-spectral domains. A masked self-supervised multi-dimensional pre-training strategy is further developed to learn generalizable spectrum representations across diverse wireless environments. Once pre-trained, FM-RME supports zero-shot inference for multi-dimensional RME, including spatial, temporal, and spectral estimation, without scenario-specific retraining. Simulation results verify that FM-RME exhibits desired learning performance across diverse datasets and zero-shot generalization capabilities beyond existing RME methods.