UniGaze: Towards Universal Gaze Estimation via Large-scale Pre-Training
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916651679612928 |
|---|---|
| author | Qin, Jiawei Zhang, Xucong Sugano, Yusuke |
| author_facet | Qin, Jiawei Zhang, Xucong Sugano, Yusuke |
| contents | Despite decades of research on data collection and model architectures, current gaze estimation models encounter significant challenges in generalizing across diverse data domains. Recent advances in self-supervised pre-training have shown remarkable performances in generalization across various vision tasks. However, their effectiveness in gaze estimation remains unexplored. We propose UniGaze, for the first time, leveraging large-scale in-the-wild facial datasets for gaze estimation through self-supervised pre-training. Through systematic investigation, we clarify critical factors that are essential for effective pretraining in gaze estimation. Our experiments reveal that self-supervised approaches designed for semantic tasks fail when applied to gaze estimation, while our carefully designed pre-training pipeline consistently improves cross-domain performance. Through comprehensive experiments of challenging cross-dataset evaluation and novel protocols including leave-one-dataset-out and joint-dataset settings, we demonstrate that UniGaze significantly improves generalization across multiple data domains while minimizing reliance on costly labeled data. source code and model are available at https://github.com/ut-vision/UniGaze. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_02307 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | UniGaze: Towards Universal Gaze Estimation via Large-scale Pre-Training Qin, Jiawei Zhang, Xucong Sugano, Yusuke Computer Vision and Pattern Recognition Despite decades of research on data collection and model architectures, current gaze estimation models encounter significant challenges in generalizing across diverse data domains. Recent advances in self-supervised pre-training have shown remarkable performances in generalization across various vision tasks. However, their effectiveness in gaze estimation remains unexplored. We propose UniGaze, for the first time, leveraging large-scale in-the-wild facial datasets for gaze estimation through self-supervised pre-training. Through systematic investigation, we clarify critical factors that are essential for effective pretraining in gaze estimation. Our experiments reveal that self-supervised approaches designed for semantic tasks fail when applied to gaze estimation, while our carefully designed pre-training pipeline consistently improves cross-domain performance. Through comprehensive experiments of challenging cross-dataset evaluation and novel protocols including leave-one-dataset-out and joint-dataset settings, we demonstrate that UniGaze significantly improves generalization across multiple data domains while minimizing reliance on costly labeled data. source code and model are available at https://github.com/ut-vision/UniGaze. |
| title | UniGaze: Towards Universal Gaze Estimation via Large-scale Pre-Training |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.02307 |