# RadioDUN: A Physics-Inspired Deep Unfolding Network for Radio Map Estimation

arXiv: https://arxiv.org/abs/2506.08418 · HTML: https://mlsanity.com/paper/2506.08418/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 49 references that are in the map.
- First posted on arXiv 10 Jun 2025.

## Builds on (most cited first, 18 of 18)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [A Comprehensive Survey on Transfer Learning](https://mlsanity.com/paper/1911.02685/) (2019)
- [Multi-Scale Context Aggregation by Dilated Convolutions](https://mlsanity.com/paper/1511.07122/) (2015)
- [Plug-and-Play ADMM for Image Restoration: Fixed Point Convergence and Applications](https://mlsanity.com/paper/1605.01710/) (2016)
- [RadioUNet: Fast Radio Map Estimation with Convolutional Neural Networks](https://mlsanity.com/paper/1911.09002/) (2019)
- [Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstruction](https://mlsanity.com/paper/2111.07910/) (2021)
- [RME-GAN: A Learning Framework for Radio Map Estimation based on Conditional Generative Adversarial Network](https://mlsanity.com/paper/2212.12817/) (2022)
- [ISTA-Net++: Flexible Deep Unfolding Network for Compressive Sensing](https://mlsanity.com/paper/2103.11554/) (2021)
- [6G Wireless Communication Systems: Applications, Requirements, Technologies, Challenges, and Research Directions](https://mlsanity.com/paper/1909.11315/) (2019)
- [Radio Map Estimation: A Data-Driven Approach to Spectrum Cartography](https://mlsanity.com/paper/2202.03269/) (2022)
- [A Scalable and Generalizable Pathloss Map Prediction](https://mlsanity.com/paper/2312.03950/) (2023)
- [Generative AI on SpectrumNet: An Open Benchmark of Multiband 3D Radio Maps](https://mlsanity.com/paper/2408.15252/) (2024)
- [Optimization-Inspired Cross-Attention Transformer for Compressive Sensing](https://mlsanity.com/paper/2304.13986/) (2023)
- [Sparse Bayesian Learning-Based Hierarchical Construction for 3D Radio Environment Maps Incorporating Channel Shadowing](https://mlsanity.com/paper/2403.08323/) (2024)
- [PUERT: Probabilistic Under-sampling and Explicable Reconstruction Network for CS-MRI](https://mlsanity.com/paper/2204.11189/) (2022)
- [Cloud-Magnetic Resonance Imaging System: In the Era of 6G and Artificial Intelligence](https://mlsanity.com/paper/2310.11641/) (2023)

## Built on by (most cited first, 2 of 2)

- [Bridging the Sampling Distribution Shift in Radio Map Estimation: A Trajectory-Aware Paradigm](https://mlsanity.com/paper/2605.28234/) (2026)
- [RadioFormer3D: Weakly Supervised 3D Radio Map Estimation in Low-Altitude Airspace via Generative Modeling](https://mlsanity.com/paper/2605.29538/) (2026)

## Abstract (arXiv)

The radio map represents the spatial distribution of spectrum resources within a region, supporting efficient resource allocation and interference mitigation. However, it is difficult to construct a dense radio map as a limited number of samples can be measured in practical scenarios. While existing works have used deep learning to estimate dense radio maps from sparse samples, they are hard to integrate with the physical characteristics of the radio map. To address this challenge, we cast radio map estimation as the sparse signal recovery problem. A physical propagation model is further incorporated to decompose the problem into multiple factor optimization sub-problems, thereby reducing recovery complexity. Inspired by the existing compressive sensing methods, we propose the Radio Deep Unfolding Network (RadioDUN) to unfold the optimization process, achieving adaptive parameter adjusting and prior fitting in a learnable manner. To account for the radio propagation characteristics, we develop a dynamic reweighting module (DRM) to adaptively model the importance of each factor for the radio map. Inspired by the shadowing factor in the physical propagation model, we integrate obstacle-related factors to express the obstacle-induced signal stochastic decay. The shadowing loss is further designed to constrain the factor prediction and act as a supplementary supervised objective, which enhances the performance of RadioDUN. Extensive experiments have been conducted to demonstrate that the proposed method outperforms the state-of-the-art methods. Our code will be made publicly available upon publication.