Rendering photorealistic head avatars from arbitrary viewpoints is crucial for various applications like virtual reality. Although previous methods based on Neural Radiance Fields (NeRF) can achieve impressive results, they lack fidelity and efficiency. Recent methods using 3D Gaussian Splatting (3DGS) have improved rendering quality and real-time performance but still require significant storage overhead. In this paper, we introduce a method called GraphAvatar that utilizes Graph Neural Networks (GNN) to generate 3D Gaussians for the head avatar. Specifically, GraphAvatar trains a geometric GNN and an appearance GNN to generate the attributes of the 3D Gaussians from the tracked mesh. Therefore, our method can store the GNN models instead of the 3D Gaussians, significantly reducing the storage overhead to just 10MB. To reduce the impact of face-tracking errors, we also present a novel graph-guided optimization module to refine face-tracking parameters during training. Finally, we introduce a 3D-aware enhancer for post-processing to enhance the rendering quality. We conduct comprehensive experiments to demonstrate the advantages of GraphAvatar, surpassing existing methods in visual fidelity and storage consumption. The ablation study sheds light on the trade-offs between rendering quality and model size.
从任意视角渲染光真实感的头像是虚拟现实等多种应用中的关键任务。尽管基于神经辐射场（NeRF）的现有方法能够取得令人印象深刻的效果，但在保真度和效率方面仍存在不足。近期基于三维高斯点云（3D Gaussian Splatting, 3DGS）的方法改善了渲染质量并实现了实时性能，但其存储开销仍然较高。 为了解决这一问题，我们提出了 GraphAvatar，一种利用图神经网络（Graph Neural Networks, GNN）生成头像三维高斯的方法。具体而言，GraphAvatar 通过训练几何 GNN 和外观 GNN，从追踪的网格中生成三维高斯的属性。因此，我们的方法仅需存储 GNN 模型，而不需要存储三维高斯本身，将存储开销显著降低至仅 10MB。 为减轻面部追踪误差的影响，我们引入了一种基于图引导的优化模块，用于在训练过程中优化面部追踪参数。此外，我们提出了一个三维感知增强模块，用于后处理以提升渲染质量。 通过全面实验，我们验证了 GraphAvatar 在视觉保真度和存储消耗方面的显著优势。消融研究进一步探讨了渲染质量与模型大小之间的权衡，表明 GraphAvatar 在性能与存储效率上的平衡具有重要意义。