MARS: Radio Map Super-resolution and Reconstruction Method under Sparse Channel Measurements

TL;DR

This paper introduces MARS, a novel super-resolution method combining CNNs and Transformers to accurately reconstruct radio maps from sparse measurements, improving performance and generalization in various environments.

Contribution

MARS is a new multi-scale aware approach that enhances radio map reconstruction by integrating CNNs and Transformers with feature fusion and residual connections.

Findings

MARS outperforms baseline models in MSE and SSIM metrics.

It maintains low computational cost while improving accuracy.

Effective across different scenes and antenna locations.

Abstract

Radio maps reflect the spatial distribution of signal strength and are essential for applications like smart cities, IoT, and wireless network planning. However, reconstructing accurate radio maps from sparse measurements remains challenging. Traditional interpolation and inpainting methods lack environmental awareness, while many deep learning approaches depend on detailed scene data, limiting generalization. To address this, we propose MARS, a Multi-scale Aware Radiomap Super-resolution method that combines CNNs and Transformers with multi-scale feature fusion and residual connections. MARS focuses on both global and local feature extraction, enhancing feature representation across different receptive fields and improving reconstruction accuracy. Experiments across different scenes and antenna locations show that MARS outperforms baseline models in both MSE and SSIM, while maintaining low computational cost, demonstrating strong practical potential.