S-Avatar：基于单张图像的扩散引导高斯头部化身
S-Avatar: Diffusion-Guided Gaussian Head Avatars from a Single Image
- KAIST（韩国科学技术院）
- KAIST KI-ITC ARRC（韩国科学技术院KI-ITC ARRC）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
S-Avatar通过三阶段流水线，结合扩散引导3DGS生成与FLAME控制，从单张图像生成高逼真3D头部化身，提升了3D一致性，在新视点和表情生成上优于现有方法，适用于VR/AR应用。
AI中文摘要：
我们提出了S-Avatar，一种利用扩散引导的3D模型生成模块和3D Gaussian Splatting（3DGS）动画策略，从单张图像生成逼真的3D头部化身的新方法。单张图像头部化身重建对于逼真的虚拟现实（VR）应用至关重要，但现有方法在未见过的视点下往往难以保持3D一致性。S-Avatar通过三阶段流水线解决了这一局限：首先，利用基于扩散的高斯样条生成模块直接从单张图像合成高分辨率3DGS；接着，通过优化参数和空间变换，将参数化头部模型FLAME与生成的3DGS对齐；最后，为使3DGS适配FLAME的变化，我们构建了编码初始样条与FLAME之间空间关系的绑定模板，随后可通过该绑定模板变形3DGS，实时渲染动态3D头部化身。通过将扩散引导的规范3DGS生成与基于FLAME的控制相结合，我们的方法实现了高效准确的重建，同时提升了3D一致性。在公开数据集上的评估表明，S-Avatar在新视点和表情生成方面优于最先进的方法，实现了更出色的真实感和一致性。因此，我们的方法在可访问的化身创建方面取得了重大进展，适用于广泛的VR/AR应用。项目页面可访问此https URL。
英文摘要：
We propose S-Avatar, a novel method for generating photorealistic 3D head avatars from a single image using a diffusion-guided 3D model generation module and strategies for animating 3D Gaussian Splatting (3DGS). While single-image head avatar reconstruction is crucial for lifelike Virtual Reality (VR) applications, existing approaches often struggle to preserve 3D consistency under unseen viewpoints. S-Avatar addresses this limitation through a three-stage pipeline. First, a high-resolution 3DGS is synthesized directly from a single image using a diffusion-based Gaussian splat generation module. Next, the parametric head model FLAME is aligned with the generated 3DGS by optimizing its parameters and spatial transformations. Finally, to adapt the 3DGS to FLAME variations, we construct a binding template that encodes the spatial relationship between the initial splats and FLAME. The dynamic 3D head avatar can then be rendered in real time by deforming the 3DGS with the binding template. By combining diffusion-guided canonical 3DGS generation with FLAME-based control, our method achieves efficient and accurate reconstruction with enhanced 3D consistency. Evaluations on public datasets demonstrate that S-Avatar outperforms state-of-the-art methods in novel-view and expression generation, achieving superior realism and consistency. Consequently, our approach represents a significant advance in accessible avatar creation, applicable to a wide range of VR/AR applications. The project page is available at https://github.com/hailsong/savatar.
