Tavatar：面向可动画人体化身的拓扑感知高斯属性推导
Tavatar: Topology-Aware Gaussian Attribute Derivation for Animatable Human Avatars
将高斯属性（尺度、旋转）解析地绑定到网格局部几何，而非自由学习，为基于 3DGS 的人体建模提供了一种保证拓扑一致性的参数化方案，可推广到其他需要与模板网格对齐的动态场景重建。
原文依据 we bind Gaussians to mesh faces and vertices, deriving their scales and orientations from triangle properties and local edge lengths
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论从单目视频重建高保真、可动画的人体化身仍是一项关键挑战。现有的基于 3DGS 的人体动画方法约束了高斯参数但排除了尺度，而我们认为尺度对于使人体姿态适应具有挑战性的分布外姿态至关重要。为了在未见姿态下实现鲁棒的动画，我们提出 Tavatar，它直接从局部网格几何推导尺度、旋转和其他几何属性等关键参数，而不是通过无约束优化来学习它们。这种范式转变在设计上强制了拓扑一致性，因为每个高斯都被解析地锚定到局部网格几何，继承其空间结构和变形行为。具体来说，我们将高斯绑定到网格面和顶点，从三角形属性和局部边长推导其尺度和方向，以确保连贯的表面覆盖。为了保证这种解析映射的稳定性，我们引入了一个关键的正则化项——等边正则化，以保持网格完整性。大量实验表明，Tavatar 在具有挑战性的分布外姿态上实现了更优的动画鲁棒性，与最佳基线相比，在 X-Avatar 上法线误差降低了 13.8%，在 PeopleSnapshot 上降低了 17.9%，同时保持了有竞争力的渲染质量。
英文原文摘要 1335 字符
Reconstructing high-fidelity, animatable human avatars from monocular videos remains a critical challenge. Existing 3DGS-based human animation methods constrain Gaussian parameters but exclude scale, which we argue is crucial for adapting human poses to challenging out-of-distribution poses. To achieve robust animation under unseen poses, we propose Tavatar, which derives key parameters such as scale, rotation, and other geometric attributes directly from the local mesh geometry, instead of learning them through unconstrained optimization. This paradigm shift enforces topological consistency by design, as each Gaussian is analytically anchored to the local mesh geometry, inheriting its spatial structure and deformation behavior. Specifically, we bind Gaussians to mesh faces and vertices, deriving their scales and orientations from triangle properties and local edge lengths to ensure coherent surface coverage. To ensure the stability of this analytical mapping, we introduce a crucial equilateral regularization term that preserves mesh integrity. Extensive experiments demonstrate that Tavatar achieves superior animation robustness on challenging out-of-distribution poses, reducing normal error by 13.8% on X-Avatar and 17.9% on PeopleSnapshot against the best baseline, while maintaining competitive rendering quality.