Published June 17, 2026 | Version v1

Diffusion-Based Channel Estimation: Training, Evaluation, and Testing Datasets

  • 1. ROR icon Technical University of Munich

Description

Dataset for Diffusion_channel_est

This dataset contains the NumPy .npy files used for training and testing the models in the GitHub repository:

https://github.com/benediktfesl/Diffusion_channel_est

Usage

Download and extract the dataset archive. Afterward, copy the bin/ folder to the repository root before running the training or testing scripts.

Files

Diffusion_channel_est.zip

Files (2.9 GB)

Name Size
md5:cfe59362edf8c2fc18e201b119860b74
2.9 GB Preview Download

Additional details

Related works

Is supplement to
Journal article: 10.1109/LWC.2024.3474570 (DOI)
Journal article: arXiv:2403.03545 (arXiv)

Software

References

  • B. Fesl, M. Baur, F. Strasser, M. Joham and W. Utschick, "Diffusion-Based Generative Prior for Low-Complexity MIMO Channel Estimation," in IEEE Wireless Communications Letters, vol. 13, no. 12, pp. 3493-3497, Dec. 2024, doi: 10.1109/LWC.2024.3474570.