STGA: Selective-Training Gaussian Head Avatars
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916645846384640 |
|---|---|
| author | Guo, Hanzhi Chen, Yixiao Xiaonuo, Dongye Tian, Zeyu Weng, Dongdong Luo, Le |
| author_facet | Guo, Hanzhi Chen, Yixiao Xiaonuo, Dongye Tian, Zeyu Weng, Dongdong Luo, Le |
| contents | We propose selective-training Gaussian head avatars (STGA) to enhance the details of dynamic head Gaussian. The dynamic head Gaussian model is trained based on the FLAME parameterized model. Each Gaussian splat is embedded within the FLAME mesh to achieve mesh-based animation of the Gaussian model. Before training, our selection strategy calculates the 3D Gaussian splat to be optimized in each frame. The parameters of these 3D Gaussian splats are optimized in the training of each frame, while those of the other splats are frozen. This means that the splats participating in the optimization process differ in each frame, to improve the realism of fine details. Compared with network-based methods, our method achieves better results with shorter training time. Compared with mesh-based methods, our method produces more realistic details within the same training time. Additionally, the ablation experiment confirms that our method effectively enhances the quality of details. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_05196 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | STGA: Selective-Training Gaussian Head Avatars Guo, Hanzhi Chen, Yixiao Xiaonuo, Dongye Tian, Zeyu Weng, Dongdong Luo, Le Graphics Computer Vision and Pattern Recognition We propose selective-training Gaussian head avatars (STGA) to enhance the details of dynamic head Gaussian. The dynamic head Gaussian model is trained based on the FLAME parameterized model. Each Gaussian splat is embedded within the FLAME mesh to achieve mesh-based animation of the Gaussian model. Before training, our selection strategy calculates the 3D Gaussian splat to be optimized in each frame. The parameters of these 3D Gaussian splats are optimized in the training of each frame, while those of the other splats are frozen. This means that the splats participating in the optimization process differ in each frame, to improve the realism of fine details. Compared with network-based methods, our method achieves better results with shorter training time. Compared with mesh-based methods, our method produces more realistic details within the same training time. Additionally, the ablation experiment confirms that our method effectively enhances the quality of details. |
| title | STGA: Selective-Training Gaussian Head Avatars |
| topic | Graphics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.05196 |