StyGazeTalk: Learning Stylized Generation of Gaze and Head Dynamics
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_ | 1866908742894747648 |
|---|---|
| author | Shi, Chengwei Cao, Chong |
| author_facet | Shi, Chengwei Cao, Chong |
| contents | Gaze and head movements play a central role in expressive 3D media, human-agent interaction, and immersive communication. Existing works often model facial components in isolation and lack mechanisms for generating personalized, style-aware gaze behaviors. We propose StyGazeTalk, a multimodal framework that synthesizes synchronized gaze-head dynamics with controllable styles. To support high-fidelity training, we construct HAGE, a high-precision multimodal dataset containing eye-tracking data, audio, head pose, and 3D facial parameters. Experiments show that our method produces temporally coherent, style-consistent gaze-head motions, enhancing realism in 3D face generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_17168 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | StyGazeTalk: Learning Stylized Generation of Gaze and Head Dynamics Shi, Chengwei Cao, Chong Graphics Computer Vision and Pattern Recognition Gaze and head movements play a central role in expressive 3D media, human-agent interaction, and immersive communication. Existing works often model facial components in isolation and lack mechanisms for generating personalized, style-aware gaze behaviors. We propose StyGazeTalk, a multimodal framework that synthesizes synchronized gaze-head dynamics with controllable styles. To support high-fidelity training, we construct HAGE, a high-precision multimodal dataset containing eye-tracking data, audio, head pose, and 3D facial parameters. Experiments show that our method produces temporally coherent, style-consistent gaze-head motions, enhancing realism in 3D face generation. |
| title | StyGazeTalk: Learning Stylized Generation of Gaze and Head Dynamics |
| topic | Graphics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.17168 |