GazeMorph: Reducing Eye-Tracking Measurement Error by Fixation-to-Content Alignment ETRA021
Proceedings of the ACM on Human-Computer Interaction · 31.05.2026 · 10 (3) · 1-15
DOI: 10.1145/3806035 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the ACM on Human-Computer Interaction, online erschienen am 28.05.2026. Verfasst von Almaz Shangareev und 1 weiteren Autor:innen. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
We introduce GazeMorph, a 3D UNet-style neural network that aligns measured fixation points to on-screen content to reduce eye-tracking measurement error in realistic settings. The model takes as input a time-stacked sequence of fixation maps and a content structure, and predicts a dense displacement field constrained by spatial and temporal smoothness that enforces coherent local motion and by a soft fold penalty discouraging folded or self-overlapping deformations. Trained on ZuCo-based pages where fixation maps are elastically distorted to emulate spatial noise of eye-trackers, GazeMorph amortizes fixation correction and consistently reduces the average fixation-position error across all noise levels. These results demonstrate that on-content alignment serves as an effective post-processing step for robust gaze correction, complementing hardware calibration and improving the reliability of eye-tracking data in practical applications.
Zitieren
APA
Shangareev, A., & Stupnikov, S. (2026). GazeMorph: Reducing Eye-Tracking Measurement Error by Fixation-to-Content Alignment ETRA021. Proceedings of the ACM on Human-Computer Interaction, 10(3), 1-15. https://doi.org/10.1145/3806035
Vancouver
Shangareev A, Stupnikov S. GazeMorph: Reducing Eye-Tracking Measurement Error by Fixation-to-Content Alignment ETRA021. Proceedings of the ACM on Human-Computer Interaction. 2026;10(3):1-15. doi:10.1145/3806035
BibTeX
@article{Shangareev2026,
author = {Shangareev, Almaz and Stupnikov, Sergey},
title = {GazeMorph: Reducing Eye-Tracking Measurement Error by Fixation-to-Content Alignment ETRA021},
journal = {Proceedings of the ACM on Human-Computer Interaction},
year = {2026},
volume = {10},
number = {3},
pages = {1--15},
doi = {10.1145/3806035}
}
EUVIMED