Reproduce “DyRadio: Spatiotemporal Diffusion for Dynamic Radio Map Reconstruction” 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
Zhijie Fan, Zhifeng Zhao, Rongpeng Li
DyRadio reconstructs radio maps from sparse observations across changing frames while estimating noise. It combines a U-Net for maps and propagation features with a diffusion transformer that denoises neighboring frames jointly. On simulated traffic tests, at 2% sampling and noise standard deviation 0.05, DyRadio achieves 34.24 dB PSNR versus 31.94 dB for RadioMapMotion; results are limited to this dataset and protocol.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.