Reproduce “Reconstructing Visual Stimulus Images from EEG Signals Based on Deep Visual Representation Model” 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

Hongguang Pan, Zhuoyi Li, Yunpeng Fu, Xuebin Qin, Jianchen Hu

DVRM reconstructs images from EEG recorded while participants view printed characters. It learns a representation from paired image-EEG examples, then uses EEG alone at test time to decode an image. Across six two-character settings and four participants, mean PCC was 0.522 ± 0.047 and mean SSIM was 0.433 ± 0.044. These results concern constrained stimuli, not arbitrary images.

Summary by alphaXiv.

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