GazePrior: Zero-Shot AR/VR Eye Tracking via Learned 3D Gaze Reconstruction
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916036050157568 |
|---|---|
| author | Dumery, Corentin Colmenares, David Fix, Alexander Fua, Pascal Behrooz, Ali Kundu, Jogendra |
| author_facet | Dumery, Corentin Colmenares, David Fix, Alexander Fua, Pascal Behrooz, Ali Kundu, Jogendra |
| contents | Eye tracking (ET) is a foundational technology for advanced AR/VR applications. However, training ET models for every new ET device is challenging: real data collection is costly and time-consuming, while existing synthetic data generation methods lack realism. To remove the need for additional data collection while maintaining data quality, we introduce a data-driven 3D prior that models the distribution of human eyes across diverse identities, gaze directions, and light settings. This model, which we coin GazePrior, then enables sparse-input 3D reconstruction of annotated data collected with previous ET devices, which can in turn be rendered from the cameras of any target ET device. Our approach synthesizes data with the realism, diversity and ground-truth accuracy of real data collection without its prohibitive costs. Our experiments demonstrate that ET models trained with our synthesized data outperform previous zero-shot methods, achieving higher accuracy and robustness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_22359 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GazePrior: Zero-Shot AR/VR Eye Tracking via Learned 3D Gaze Reconstruction Dumery, Corentin Colmenares, David Fix, Alexander Fua, Pascal Behrooz, Ali Kundu, Jogendra Computer Vision and Pattern Recognition Eye tracking (ET) is a foundational technology for advanced AR/VR applications. However, training ET models for every new ET device is challenging: real data collection is costly and time-consuming, while existing synthetic data generation methods lack realism. To remove the need for additional data collection while maintaining data quality, we introduce a data-driven 3D prior that models the distribution of human eyes across diverse identities, gaze directions, and light settings. This model, which we coin GazePrior, then enables sparse-input 3D reconstruction of annotated data collected with previous ET devices, which can in turn be rendered from the cameras of any target ET device. Our approach synthesizes data with the realism, diversity and ground-truth accuracy of real data collection without its prohibitive costs. Our experiments demonstrate that ET models trained with our synthesized data outperform previous zero-shot methods, achieving higher accuracy and robustness. |
| title | GazePrior: Zero-Shot AR/VR Eye Tracking via Learned 3D Gaze Reconstruction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.22359 |