通过逐帧选择性优化高斯点，提升动态人脸建模的细节真实感。
STGA: Selective-Training Gaussian Head Avatars
- 每帧只优化部分高斯点，其余冻结以聚焦细节
- 相比网络方法训练更快，细节更逼真
- 适合追求高质量人脸动画的开发者
我们提出选择性训练高斯人脸头像（STGA），以增强动态头像高斯模型的细节表现。该动态头像高斯模型基于FLAME参数化模型构建，每个高斯点嵌入在FLAME网格中，实现基于网格的动画。训练前，我们的选择策略计算每帧需优化的3D高斯点。在每帧训练中，仅优化选定的高斯点参数，其余点保持冻结。因此，每帧参与优化的点不同，从而提升细微结构的真实感。与基于网络的方法相比，本方法在更短训练时间内获得更好效果；与基于网格的方法相比，在相同训练时间下生成更真实的细节。消融实验验证了该方法能有效提升细节质量。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。