Reproduce “Step-Aware Residual-Guided Diffusion for EEG Spatial Super-Resolution” 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
Hongjun Liu, Leyu Zhou, Zijianghao Yang, Chao Yao
SRGDiff reconstructs high-density EEG signals from sparse electrode recordings using diffusion. At each denoising step, it predicts a correction from low-density input and modulates the update according to the step. On Localize-MI at 16× upsampling, its held-out test-set NMSE is 0.3457 ± 0.002, compared with 0.4076 ± 0.002 for DDPMEEG. This reconstruction comparison does not establish equivalence to a measured high-density recording.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.