# Fusion of Pervasive RF Data with Spatial Images via Vision Transformers for Enhanced Mapping in Smart Cities

arXiv: https://arxiv.org/abs/2508.03736 · HTML: https://mlsanity.com/paper/2508.03736/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 48 references that are in the map.
- First posted on arXiv 31 Jul 2025.

## Builds on (most cited first, 14 of 14)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Sionna: An Open-Source Library for Next-Generation Physical Layer Research](https://mlsanity.com/paper/2203.11854/) (2022)
- [RadioUNet: Fast Radio Map Estimation with Convolutional Neural Networks](https://mlsanity.com/paper/1911.09002/) (2019)
- [MetaLoc: Learning to Learn Wireless Localization](https://mlsanity.com/paper/2211.04258/) (2022)
- [RadioNet: Transformer based Radio Map Prediction Model For Dense Urban Environments](https://mlsanity.com/paper/2105.07158/) (2021)
- [Correcting rural building annotations in OpenStreetMap using convolutional neural networks](https://mlsanity.com/paper/1901.08190/) (2019)
- [Millimeter-wave Mobile Sensing and Environment Mapping: Models, Algorithms and Validation](https://mlsanity.com/paper/2102.11593/) (2021)
- [Vision Transformers for Efficient Indoor Pathloss Radio Map Prediction](https://mlsanity.com/paper/2412.09507/) (2024)
- [IPP-Net: A Generalizable Deep Neural Network Model for Indoor Pathloss Radio Map Prediction](https://mlsanity.com/paper/2501.06414/) (2025)
- [ML-based Approaches for Wireless NLOS Localization: Input Representations and Uncertainty Estimation](https://mlsanity.com/paper/2304.11396/) (2023)
- [Outdoor Environment Reconstruction with Deep Learning on Radio Propagation Paths](https://mlsanity.com/paper/2402.17336/) (2024)
- [Wireless Localization for mmWave Networks in Urban Environments](https://mlsanity.com/paper/1805.11208/) (2018)
- [TransPathNet: A Novel Two-Stage Framework for Indoor Radio Map Prediction](https://mlsanity.com/paper/2501.16023/) (2025)

## Abstract (arXiv)

In this paper, we present a deep learning-based approach that integrates the DINOv2 architecture to improve building mapping by combining (possibly erroneous) maps from open-source platforms with pervasive radio frequency (RF) data collected from multiple wireless user equipments and base stations. Unlike prior methods, our approach leverages a vision transformer-based architecture to jointly process both RF and map modalities within a unified framework, effectively capturing spatial dependencies and structural priors for enhanced mapping accuracy. For the evaluation purposes, we employ a synthetic dataset co-produced by Huawei. To address the challenges associated with real-world data imperfections, we introduce controlled noise to its RF data so as to simulate real-world conditions. Additionally, we develop and train a model that leverages only aggregated path loss information to tackle the mapping problem. We measure the results according to three performance metrics: the Jaccard index (intersection over union, IoU), the Hausdorff distance, and the Chamfer distance. Our design achieves a macro IoU of 65.3%, significantly surpassing (i) the erroneous maps baseline, which yields 40.1%, (ii) an RF-only method from the literature, which yields 37.3%, and (iii) a non-AI fusion baseline that we designed which yields 42.2%. The comparative evaluation highlights the limitations of relying solely on RF data or on spatial data, as well as the effectiveness that AI can have on fusing data towards enhancing smart city mapping accuracy. We further validate our method on real-world data from the Oslo region, complementing the synthetic evaluation with a real deployment setting, where our best fusion model reaches 64.9% macro IoU. We additionally outline a strategy for deploying the model over larger areas by tiling the region with overlapping windows.