Reproduce “Radio Map Prediction from Aerial Images and Application to Coverage Optimization” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Fabian Jaensch, Giuseppe Caire, Begüm Demir

The authors predict site-specific radio maps from aerial imagery, with optional height data, using UNetDCN, a U-Net-style model with deformable convolutions. On held-out Berlin city maps, image-only UNetDCN achieves 0.088 grayscale RMSE, corresponding to about 6.7 dB, versus 0.091 for PMNet. The targets are ray-tracing simulations, so this does not establish field accuracy or transfer beyond the tested setting.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.