mlsanityData to 7 Oct 2026

Generative AI on SpectrumNet: An Open Benchmark of Multiband 3D Radio Maps

arXiv 2408.15252 ↗First posted 9 Aug 2024eess.SP cs.AIcited by 14

Not on the map. Why?

Abstract (arXiv)

Radio map is an efficient demonstration for visually displaying the wireless signal coverage within a certain region. It has been considered to be increasingly helpful for the future sixth generation (6G) of wireless networks, as wireless nodes are becoming more crowded and complicated. However, the construction of high resolution radio map is very challenging due to the sparse sampling in practical systems. Generative artificial intelligence (AI), which is capable to create synthetic data to fill in gaps in real-world measurements, is an effective technique to construct high precision radio maps. Currently, generative models for radio map construction are trained with two-dimension (2D) single band radio maps in urban scenario, which has poor generalization in diverse terrain scenarios, spectrum bands, and heights. To tackle this problem, we provide a multiband three-dimension (3D) radio map dataset with consideration of terrain and climate information, named SpectrumNet. It is the largest radio map dataset in terms of dimensions and scale, which contains the radio map of 3 spacial dimensions, 5 frequency bands, 11 terrain scenarios, and 3 climate scenarios. We introduce the parameters and settings for the SpectrumNet dataset generation, and evaluate three baseline methods for radio map construction based on the SpectrumNet dataset. Experiments show the necessity of the SpectrumNet dataset for training models with strong generalization in spacial, frequency, and scenario domains. Future works on the SpectrumNet dataset are also discussed, including the dataset expansion and calibration, as well as the extended studies on generative models for radio map construction based on the SpectrumNet dataset.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 19 of its 49 references that are in the map. First posted on arXiv 9 Aug 2024.

Builds on

19 of 49 references.

References · 19

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  3. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  4. 2021Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentationcited by 1,218
  5. 2019RadioUNet: Fast Radio Map Estimation with Convolutional Neural Networkscited by 126
  6. 2022RME-GAN: A Learning Framework for Radio Map Estimation based on Conditional Generative Adversarial Networkcited by 50
  7. 2020Deep Completion Autoencoders for Radio Map Estimationcited by 39
  8. 20216G Internet of Things: A Comprehensive Surveycited by 39
  9. 2022Radio Map Estimation: A Data-Driven Approach to Spectrum Cartographycited by 31
  10. 2022Dataset of Pathloss and ToA Radio Maps With Localization Applicationcited by 27
  11. 2020Simultaneous Navigation and Radio Mapping for Cellular-Connected UAV with Deep Reinforcement Learningcited by 26
  12. 2019Radio Map Based 3D Path Planning for Cellular-Connected UAVcited by 24
7 more
  1. 2023Generative AI-empowered Simulation for Autonomous Driving in Vehicular Mixed Reality Metaversescited by 22
  2. 2024RadioGAT: A Joint Model-based and Data-driven Framework for Multi-band Radiomap Reconstruction via Graph Attention Networkscited by 16
  3. 2021Deep Spectrum Cartography: Completing Radio Map Tensors Using Learned Neural Modelscited by 14
  4. 2019Radio Localization and Mapping with Reconfigurable Intelligent Surfacescited by 10
  5. 2024Radio Map Estimation -- An Open Dataset with Directive Transmitter Antennas and Initial Experimentscited by 7
  6. 2024ACT-GAN: Radio map construction based on generative adversarial networks with ACT blockscited by 6
  7. 2023Velocity-Based Channel Charting with Spatial Distribution Map Matchingcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 9.

14 papers.

Sort:

By area:

  1. 2025RadioDiff-3D: A 3D×3D Radio Map Dataset and Generative Diffusion Based Benchmark for 6G Environment-Aware Communicationcited by 16
  2. 2026U6G XL-MIMO Radiomap Prediction: Multi-Config Dataset and Beam Map Approachcited by 4
  3. 2026Sparse Gain Radio Map Reconstruction With Geometry Priors and Uncertainty-Guided Measurement Selectioncited by 3
  4. 2025RadioFormer: A Multiple-Granularity Radio Map Estimation Transformer with 1textpertenthousand Spatial Samplingcited by 2
  5. 2025RadioDUN: A Physics-Inspired Deep Unfolding Network for Radio Map Estimationcited by 2
  6. 2026Geometry-Aware Cross-Height Channel Knowledge Map Prediction for UAV-Assisted Communications With Uncertainty-Guided 3D Sensingcited by 1
  7. 2025UrbanMIMOMap: A Ray-Traced MIMO CSI Dataset with Precoding-Aware Maps and Benchmarkscited by 0
  8. 2025RadioMapMotion: A Dataset and Baseline for Proactive Spatio-Temporal Radio Environment Predictioncited by 0
  9. 2026RadioGen3D: 3D Radio Map Generation via Adversarial Learning on Large-Scale Synthetic Datacited by 0
  10. 2026CSI-tuples-based 3D Channel Fingerprints Construction Assisted by MultiModal Learningcited by 0
  11. 2026Learned Elevation Models as a Lightweight Alternative to LiDAR for Radio Environment Map Estimationcited by 0
  12. 2026Bridging the Sampling Distribution Shift in Radio Map Estimation: A Trajectory-Aware Paradigmcited by 0
2 more
  1. 2026RadioFormer3D: Weakly Supervised 3D Radio Map Estimation in Low-Altitude Airspace via Generative Modelingcited by 0
  2. 2026RadioDiff-v2: Generative Angular Radio Maps for Multi-Beam Selection and Localizationcited by 0