UrbanRadio3D

---

📡 Welcome to the RadioDiff Family

Radio map construction via generative diffusion models — UNIC Lab, Xidian University

---

🔷 Base Backbone

RadioDiff — The foundational diffusion model for radio map construction.   📄 Paper  |  💻 Code  | 

---

🔬 Physics-Informed Extensions

RadioDiff-k² — PINN-enhanced diffusion guided by the Helmholtz equation.   📄 Paper  |  💻 Code  | 

iRadioDiff — Indoor radio map construction with physical information integration.   📄 Paper  |  💻 Code  |   

---

⚡ Efficiency & Dynamics

RadioDiff-Turbo — Efficiency-enhanced RadioDiff for accelerated inference.   📄 Paper  | 

RadioDiff-Flux — Adaptive reconstruction under dynamic environments and base station location changes.   📄 Paper  | 

---

🌐 Extended Scenarios

RadioDiff-3D — 3D radio map construction with the UrbanRadio3D dataset.   📄 Paper  |  💻 Code  | 

RadioDiff-FS — Few-shot learning for radio map construction with limited measurements.   📄 Paper  |  💻 Code  | 

---

📶 Sparse Measurement & Localization

RadioDiff-Inverse — Sparse measurement-based radio map recovery for ISAC applications.   📄 Paper  |  💻 Code  | 

RadioDiff-Loc — Sparse measurement-based NLoS localization using diffusion models.   📄 Paper  | 

---

📚 For a comprehensive categorized overview of radio map research, visit Awesome-Radio-Map-Categorized.

---

This is the demo of the dataset for UrbanRadio3D, which is accepted by IEEE TNSE.

If you have any questions, please contact me at xcwang_1@stu.xidian.edu.cn

Citation

@ARTICLE{11083758,
  author={Wang, Xiucheng and Zhang, Qiming and Cheng, Nan and Chen, Junting and Zhang, Zezhong and Li, Zan and Cui, Shuguang and Shen, Xuemin},
  journal={IEEE Transactions on Network Science and Engineering}, 
  title={RadioDiff-3D: A 3D× 3D Radio Map Dataset and Generative Diffusion Based Benchmark for 6G Environment-Aware Communication}, 
  year={2025},
  volume={},
  number={},
  pages={1-18},
  doi={10.1109/TNSE.2025.3590545}}

Dataset Description

All datasets used in this project can be accessed via the following cloud storage links:

• Baidu Cloud Drive: [link]
  Extraction Code is required.

• OneDrive: [link]
  Extraction Code is required.

• For the Extraction Code, please click [link]

The extraction code is located at the top of the redirect page after you complete the questionnaire. If you cannot find it, you may contact us via email at xcwang_1@stu.xidian.edu.cn.

Dataset Splits

We have provided recommended splits of the dataset into training and testing sets to facilitate standardized model training and evaluation.

File Description

• Building_Infomation.zip
  This archive contains information on building heights and their spatial distribution, which serves as critical geometric features for wireless communication environment modeling.

• Naming Convention for RM Maps
  Each RM (Radio Map) image file follows the naming format:
  xxx_Xxxx_Yxx.png
  Where:

  • xxx indicates the building distribution map index
  • Xxxx indicates the X-coordinate of the base station
  • Yxx indicates the Y-coordinate of the base station

This naming scheme allows precise identification of the RM map's corresponding building environment and base station location, facilitating further analysis and experimental reproducibility.

---

For any questions regarding dataset usage or structure, please feel free to contact the project team for further assistance.