Reproduce “An Affordable, Wearable Stereo-Eye-Tracking Platform” 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
Alexander Zimmer, Yasmeen Abdrabou, Enkelejda Kasneci
Researchers at the Technical University of Munich developed an open-source, wearable stereo eye-tracking platform using affordable off-the-shelf and 3D-printable components. This platform provides synchronized multi-camera data and flexible configurations to facilitate the development, comparison, and benchmarking of diverse eye-tracking algorithms, including stereo and glint-based methods, under consistent sensing conditions.
Key insights
- An affordable, open-source wearable eye-tracking platform can be constructed from readily available components, significantly lowering the barrier to entry for advanced algorithm development.
- A modular hardware design combined with a robust calibration procedure enables the simultaneous support of multiple eye-tracking paradigms (e.g., stereo, glint-based) within a single system.
- Prioritizing research flexibility over end-user robustness in hardware design allows for systematic comparison and development of hybrid eye-tracking algorithms under consistent sensing conditions.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.