VGGT-HPE: Reframing Head Pose Estimation as Relative Pose Prediction
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908954771062784 |
|---|---|
| author | Vasileiou, Vasiliki Filntisis, Panagiotis P. Maragos, Petros Daniilidis, Kostas |
| author_facet | Vasileiou, Vasiliki Filntisis, Panagiotis P. Maragos, Petros Daniilidis, Kostas |
| contents | Monocular head pose estimation is traditionally formulated as direct regression from a single image to an absolute pose. This paradigm forces the network to implicitly internalize a dataset-specific canonical reference frame. In this work, we argue that predicting the relative rigid transformation between two observed head configurations is a fundamentally easier and more robust formulation. We introduce VGGT-HPE, a relative head pose estimator built upon a general-purpose geometry foundation model. Finetuned exclusively on synthetic facial renderings, our method sidesteps the need for an implicit anchor by reducing the problem to estimating a geometric displacement from an explicitly provided anchor with a known pose. As a practical benefit, the relative formulation also allows the anchor to be chosen at test time - for instance, a near-neutral frame or a temporally adjacent one - so that the prediction difficulty can be controlled by the application. Despite zero real-world training data, VGGT-HPE achieves state-of-the-art results on the BIWI benchmark, outperforming established absolute regression methods trained on mixed and real datasets. Through controlled easy- and hard-pair benchmarks, we also systematically validate our core hypothesis: relative prediction is intrinsically more accurate than absolute regression, with the advantage scaling alongside the difficulty of the target pose. Project page and code: https://vasilikivas.github.io/VGGT-HPE |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_10106 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | VGGT-HPE: Reframing Head Pose Estimation as Relative Pose Prediction Vasileiou, Vasiliki Filntisis, Panagiotis P. Maragos, Petros Daniilidis, Kostas Computer Vision and Pattern Recognition Monocular head pose estimation is traditionally formulated as direct regression from a single image to an absolute pose. This paradigm forces the network to implicitly internalize a dataset-specific canonical reference frame. In this work, we argue that predicting the relative rigid transformation between two observed head configurations is a fundamentally easier and more robust formulation. We introduce VGGT-HPE, a relative head pose estimator built upon a general-purpose geometry foundation model. Finetuned exclusively on synthetic facial renderings, our method sidesteps the need for an implicit anchor by reducing the problem to estimating a geometric displacement from an explicitly provided anchor with a known pose. As a practical benefit, the relative formulation also allows the anchor to be chosen at test time - for instance, a near-neutral frame or a temporally adjacent one - so that the prediction difficulty can be controlled by the application. Despite zero real-world training data, VGGT-HPE achieves state-of-the-art results on the BIWI benchmark, outperforming established absolute regression methods trained on mixed and real datasets. Through controlled easy- and hard-pair benchmarks, we also systematically validate our core hypothesis: relative prediction is intrinsically more accurate than absolute regression, with the advantage scaling alongside the difficulty of the target pose. Project page and code: https://vasilikivas.github.io/VGGT-HPE |
| title | VGGT-HPE: Reframing Head Pose Estimation as Relative Pose Prediction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.10106 |