HyperGaussians：用于高保真可动画人脸头像的高维高斯泼溅
HyperGaussians: High-Dimensional Gaussian Splatting for High-Fidelity Animatable Face Avatars
把 3D 高斯原语升级为高维多元高斯，并用「逆协方差技巧」重参数化协方差矩阵以避免高维求逆，这一表示层面的改造可直接替换现有 3DGS 管线中的原语，用于提升高频细节与非线性形变的表达能力。
原文依据 we rethink the 3D Gaussian representation itself and how to make it more expressive
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们提出 HyperGaussians，这是 3D 高斯泼溅的一种新颖扩展，用于高质量的可动画人脸头像。尽管静态人脸已取得巨大成功，但从动态视频构建的可动画头像仍处于恐怖谷之中。事实上的标准方法 3D 高斯泼溅（3DGS）通过一组 3D 高斯基元来表示人脸。3DGS 在渲染静态人脸方面表现出色，但最优方法仍难以处理非线性形变、复杂光照效果与精细细节。大多数相关工作聚焦于从表情编码预测更好的高斯参数，而我们重新思考 3D 高斯表示本身以及如何使其更具表现力。我们的洞见促成了将 3D 高斯扩展到高维多元高斯，称为「HyperGaussians」。更高的维度通过以可学习的局部嵌入为条件来提升表现力。然而，泼溅 HyperGaussians 的计算代价高昂，因为需要对高维协方差矩阵求逆。我们通过对协方差矩阵进行重参数化来解决这一问题，称为「逆协方差技巧」。该技巧提升了效率，使 HyperGaussians 能够无缝集成到现有模型中。为证明这一点，我们将 HyperGaussians 插入两种最优的人脸头像方法：FlashAvatar 与 GaussianHeadAvatar。在来自 6 个人脸数据集的 29 名受试者上的评估表明，HyperGaussians 在数值与视觉上均优于 3DGS，尤其是在眼睛、牙齿、皱纹与镜面反射等高频细节方面。
英文原文摘要 1610 字符
We introduce HyperGaussians, a novel extension of 3D Gaussian Splatting for high-quality animatable face avatars. While tremendous successes have been achieved for static faces, animatable avatars from dynamic videos still fall in the uncanny valley. The de facto standard, 3D Gaussian Splatting (3DGS), represents a face through a collection of 3D Gaussian primitives. 3DGS excels at rendering static faces, but the state-of-the-art still struggles with nonlinear deformations, complex lighting effects, and fine details. While most related works focus on predicting better Gaussian parameters from expression codes, we rethink the 3D Gaussian representation itself and how to make it more expressive. Our insights lead to a novel extension of 3D Gaussians to high-dimensional multivariate Gaussians, dubbed 'HyperGaussians'. The higher dimensionality increases expressivity through conditioning on a learnable local embedding. However, splatting HyperGaussians is computationally expensive because it requires inverting a high-dimensional covariance matrix. We solve this by reparameterizing the covariance matrix, dubbed the 'inverse covariance trick'. This trick boosts the efficiency so that HyperGaussians can be seamlessly integrated into existing models. To demonstrate this, we plug in HyperGaussians into two state-of-the-art methods for face avatars: FlashAvatar and GaussianHeadAvatar. Our evaluation on 29 subjects from 6 face datasets shows that HyperGaussians outperform 3DGS numerically and visually, particularly for high-frequency details like eyes, teeth, wrinkles, and specular reflections.