Map2APS is a new large-scale benchmark with 2.55 million samples from 51 urban maps for predicting angle power spectra from geometry, featuring a cross-map split and MS-AReg baseline with 0.948 cosine similarity.
Radiodiff: An effective generative diffusion model for sampling-free dynamic radio map construction
4 Pith papers cite this work, alongside 69 external citations. Polarity classification is still indexing.
4
Pith papers citing it
69
external citations · OpenAlex
citation-role summary
background 1
citation-polarity summary
years
2026 4roles
background 1polarities
background 1representative citing papers
PILOT unifies 2D and 3D radio map generation via physics-guided wavefront autoregressive prediction, reporting lowest NMSE on 2D benchmarks and 78% NMSE reduction with 2500x faster inference than diffusion baselines for 3D.
A learned model predicts elevation from satellite images to improve radio environment map estimation by up to 7.8% RMSE over image-only methods while eliminating LiDAR requirements during operation.
Learning-based radio map construction is taxonomized as source-aware forward prediction versus source-agnostic inverse reconstruction, spanning five neural families, optics-inspired continuous fields, and a three-level physics integration framework.
citing papers explorer
-
Map2APS: A Physically Grounded Benchmark for Direct Angle Power Spectrum Prediction from Urban Geometry
Map2APS is a new large-scale benchmark with 2.55 million samples from 51 urban maps for predicting angle power spectra from geometry, featuring a cross-map split and MS-AReg baseline with 0.948 cosine similarity.
-
PILOT: One Physics-Integrated Generation Framework to Unify 2D and 3D Radio Map Construction
PILOT unifies 2D and 3D radio map generation via physics-guided wavefront autoregressive prediction, reporting lowest NMSE on 2D benchmarks and 78% NMSE reduction with 2500x faster inference than diffusion baselines for 3D.
-
Learned Elevation Models as a Lightweight Alternative to LiDAR for Radio Environment Map Estimation
A learned model predicts elevation from satellite images to improve radio environment map estimation by up to 7.8% RMSE over image-only methods while eliminating LiDAR requirements during operation.
-
A Tutorial on Learning-Based Radio Map Construction: Data, Paradigms, and Physics-Awareness
Learning-based radio map construction is taxonomized as source-aware forward prediction versus source-agnostic inverse reconstruction, spanning five neural families, optics-inspired continuous fields, and a three-level physics integration framework.