VOGeo-Gaze: Calibration-Free, Geometry-Aware Deep Learning for Real-Time Gaze Tracking in Clinical Video-Oculography
Zhao, J.; Ahmadi, S.-A.; Decker, J.; Zwergal, A.; Eulenburg, P. z.; Flanagin, V. L.; Wuehr, M.
Show abstract
Quantitative eye movement analysis is important for neuro- logical diagnostics, yet existing video-oculography (VOG) systems typ- ically require calibration, device-specific settings, or accurate gaze la- bels. We present VOGeo-Gaze, a real-time, calibration-free, geometry- aware neural network that estimates gaze by reconstructing anatomi- cally meaningful eyeball parameters from image features. The method combines segmentation-driven projection geometry, a refraction-aware pupil correction module, and temporal anatomical stabilization, so gaze is derived from interpretable eye geometry rather than direct angular regression. Trained only on the public TEyeD dataset with weak gaze supervision, VOGeo-Gaze was evaluated on 116 clinical recordings from 17 patients and 19 healthy subjects using EyeSeeCam, a clinical gold- standard VOG system. It achieved median absolute angular errors of 0.33{whitebullet} horizontally and 0.35{whitebullet} vertically, with nearly 92% of recordings below 1{whitebullet} error while operating at >300 FPS. These results demonstrate sub-degree clinical gaze estimation without subject-specific calibration, camera intrinsics, or accurate gaze labels, providing a scalable and inter- pretable alternative to conventional VOG pipelines. Code is available at https://github.com/DSGZ-MotionLab/VOGeo-Gaze.
Matching journals
The top 9 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- Lightning Pose: improved animal pose estimation via semi-supervised learning, Bayesian ensembling, and cloud-native open-source tools 93%
- Spatial landmark detection and tissue registration with deep learning 93%
- LiftPose3D, a deep learning-based approach for transforming 2D to 3D pose in laboratory animals 93%
Similar papers in this journal
- DAMM for the detection and tracking of multiple animals within complex social and environmental settings 93%
- DeepAction: A MATLAB toolbox for automated classification of animal behavior in video 92%
- Interpretable Detection of Epiretinal Membrane from Optical Coherence Tomography with Deep Neural Networks 92%
Similar papers in this journal
- Self-supervised contrastive learning improves machine learning discrimination of full thickness macular holes from epiretinal membranes in retinal OCT scans 91%
- Uncovering the effects of model initialization on deep model generalization: A study with adult and pediatric chest X-ray images 91%
- Automated identification of abnormal infant movements from smart phone videos 90%
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.