Reproduce “Drift Calibration in Geometric Eye Tracking Systems” 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
Jiaqi Liu, Zixuan Wang, Yuhong Zhang, Dingkang Liang, Jane Hanqi Li, Tzyy-Ping Jung, Gert Cauwenberghs
The neural refiner corrects calibrated eye-trackers’ screen coordinates using known targets, combining ranked candidate corrections in a neural network trained with perturbed predictions. On disjoint test locations, mean angular error fell from 1.53° raw to 0.96°, versus 1.03° for the strongest classical method. Lower residual error was associated with higher game scores; evaluation used one device and an in-population neural split.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.