{"ID":2836060,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.22607","arxiv_id":"2511.22607","title":"GazeTrack: High-Precision Eye Tracking Based on Regularization and Spatial Computing","abstract":"Eye tracking has become increasingly important in virtual and augmented reality applications; however, the current gaze accuracy falls short of meeting the requirements for spatial computing. We designed a gaze collection framework and utilized high-precision equipment to gather the first precise benchmark dataset, GazeTrack, encompassing diverse ethnicities, ages, and visual acuity conditions for pupil localization and gaze tracking. We propose a novel shape error regularization method to constrain pupil ellipse fitting and train on open-source datasets, enhancing semantic segmentation and pupil position prediction accuracy. Additionally, we invent a novel coordinate transformation method similar to paper unfolding to accurately predict gaze vectors on the GazeTrack dataset. Finally, we built a gaze vector generation model that achieves reduced gaze angle error with lower computational complexity compared to other methods.","short_abstract":"Eye tracking has become increasingly important in virtual and augmented reality applications; however, the current gaze accuracy falls short of meeting the requirements for spatial computing. We designed a gaze collection framework and utilized high-precision equipment to gather the first precise benchmark dataset, Gaz...","url_abs":"https://arxiv.org/abs/2511.22607","url_pdf":"https://arxiv.org/pdf/2511.22607v1","authors":"[\"Xiaoyin Yang\"]","published":"2025-11-27T16:41:32Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\",\"cs.HC\",\"cs.LG\"]","methods":"[]","has_code":false}