GazeD: Context-Aware Diffusion for Accurate 3D Gaze Estimation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914274590326784 |
|---|---|
| author | Catalini, Riccardo Di Nucci, Davide Borghi, Guido Davoli, Davide Garattoni, Lorenzo Francesca, Gianpiero Kawana, Yuki Vezzani, Roberto |
| author_facet | Catalini, Riccardo Di Nucci, Davide Borghi, Guido Davoli, Davide Garattoni, Lorenzo Francesca, Gianpiero Kawana, Yuki Vezzani, Roberto |
| contents | We introduce GazeD, a new 3D gaze estimation method that jointly provides 3D gaze and human pose from a single RGB image. Leveraging the ability of diffusion models to deal with uncertainty, it generates multiple plausible 3D gaze and pose hypotheses based on the 2D context information extracted from the input image. Specifically, we condition the denoising process on the 2D pose, the surroundings of the subject, and the context of the scene. With GazeD we also introduce a novel way of representing the 3D gaze by positioning it as an additional body joint at a fixed distance from the eyes. The rationale is that the gaze is usually closely related to the pose, and thus it can benefit from being jointly denoised during the diffusion process. Evaluations across three benchmark datasets demonstrate that GazeD achieves state-of-the-art performance in 3D gaze estimation, even surpassing methods that rely on temporal information. Project details will be available at https://aimagelab.ing.unimore.it/go/gazed. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_12948 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GazeD: Context-Aware Diffusion for Accurate 3D Gaze Estimation Catalini, Riccardo Di Nucci, Davide Borghi, Guido Davoli, Davide Garattoni, Lorenzo Francesca, Gianpiero Kawana, Yuki Vezzani, Roberto Computer Vision and Pattern Recognition 68T45 I.4.8 We introduce GazeD, a new 3D gaze estimation method that jointly provides 3D gaze and human pose from a single RGB image. Leveraging the ability of diffusion models to deal with uncertainty, it generates multiple plausible 3D gaze and pose hypotheses based on the 2D context information extracted from the input image. Specifically, we condition the denoising process on the 2D pose, the surroundings of the subject, and the context of the scene. With GazeD we also introduce a novel way of representing the 3D gaze by positioning it as an additional body joint at a fixed distance from the eyes. The rationale is that the gaze is usually closely related to the pose, and thus it can benefit from being jointly denoised during the diffusion process. Evaluations across three benchmark datasets demonstrate that GazeD achieves state-of-the-art performance in 3D gaze estimation, even surpassing methods that rely on temporal information. Project details will be available at https://aimagelab.ing.unimore.it/go/gazed. |
| title | GazeD: Context-Aware Diffusion for Accurate 3D Gaze Estimation |
| topic | Computer Vision and Pattern Recognition 68T45 I.4.8 |
| url | https://arxiv.org/abs/2601.12948 |