Learning Semantic Inpainting for Animatable Gaussian Head Avatars

学习用于可动画高斯头部化身的语义修复技术

Abstract: We present SInGA, a novel method for learning Semantic Inpainting for animatable Gaussian head Avatars from a single image. Existing avatar approaches often rely on multi-view observations and lack effective handling of unobserved regions in single-view settings, limiting their applicability in such scenarios.

摘要： 我们提出了 SInGA，这是一种从单张图像学习可动画高斯头部化身（Gaussian head Avatars）语义修复的新方法。现有的化身生成方法通常依赖于多视角观测，在单视角设置下缺乏对未观测区域的有效处理，从而限制了它们在此类场景中的适用性。

To address this, we propose a semantic inpainting framework defined in UV space for completing unobserved facial regions. Our key insight lies in the structured topology of the UV representation, which provides consistent spatial correspondences and enables reliable completion of identity-specific features using the inherent symmetry cues of human faces.

为了解决这一问题，我们提出了一个在 UV 空间中定义的语义修复框架，用于补全未观测到的面部区域。我们的核心见解在于 UV 表示的结构化拓扑，它提供了空间上的一致对应关系，并利用人脸固有的对称性线索，实现了对身份特定特征的可靠补全。

We extract features from observed regions and use them to complete unobserved regions. The completed representation is then used to regress Gaussian attributes, effectively performing Gaussian inpainting. In addition, instead of relying on a single Gaussian at each surface or pixel location, we stack multiple Gaussians to enhance detail.

我们从已观测区域提取特征，并利用这些特征来补全未观测区域。随后，补全后的表示被用于回归高斯属性，从而有效地执行高斯修复。此外，我们没有在每个表面或像素位置仅依赖单个高斯，而是通过堆叠多个高斯来增强细节表现。

The resulting avatar generalizes across identities without requiring per-identity optimization and can be animated with driving inputs. Experimental results show that our method generates high-quality head avatars with improved completeness and identity preservation, while supporting realistic animation and consistent rendering from unobserved views.

由此生成的化身能够跨身份泛化，无需针对每个身份进行单独优化，并且可以通过驱动输入进行动画化。实验结果表明，我们的方法能够生成高质量的头部化身，在完整性和身份保持方面均有提升，同时支持逼真的动画效果以及从非观测视角进行的一致性渲染。