SAGA：表面对齐高斯化身
SAGA: Surface-Aligned Gaussian Avatar
AI总结：
针对单目视频重建可动画人体化身时3D高斯点易过拟合动态区域导致几何嘈杂、泛化差的问题，提出SAGA两阶段对齐策略，兼顾几何一致性与表现力，提升新视角姿态合成性能并支持快速训练和实时渲染。
摘要：
本文提出一种表面对齐高斯表示，用于从单目视频创建可动画化的人体化身，旨在提升新视角和姿态合成性能的同时，确保快速训练与实时渲染。近年来，3D高斯溅射（3DGS）已成为神经辐射场（NeRF）更高效且更具表现力的替代方案，并被用于创建动态人体化身。然而，在应用于单目动态重建这一严重不适定任务时，由于衣物褶皱或阴影等区域无法提供一致监督，高斯点易对这些持续变化的区域过拟合，导致几何结构嘈杂、变形突变，通常难以在新视角和姿态下泛化。为解决这些局限，我们提出SAGA（表面对齐高斯化身），通过将高斯点与网格对齐来强化清晰的几何结构和一致的变形，从而提升新视角与姿态下的泛化能力。与现有表现力有限、真实感低的严格对齐方法不同，SAGA采用两阶段对齐策略：先将高斯点附着于网格，再使其脱离网格，兼顾良好几何结构与高表现力。在附着阶段，我们允许高斯点在网格上流动，以提升网格附着高斯点的灵活性，这与现有将高斯点刚性绑定到固定位置的方法形成对比。在第二阶段（脱离阶段），我们引入高斯-网格对齐正则化，通过最小化高斯点与绑定三角形的位置和方向偏移，在释放高斯点表现力的同时维持几何对齐。最后，由于优化过程中高斯点可能漂移出绑定三角形，我们提出一种高效的“网格行走”策略来动态更新绑定三角形。
英文摘要：
This paper presents a Surface-Aligned Gaussian representation for creating animatable human avatars from monocular videos,aiming at improving the novel view and pose synthesis performance while ensuring fast training and real-time rendering. Recently,3DGS has emerged as a more efficient and expressive alternative to NeRF, and has been used for creating dynamic human avatars. However,when applied to the severely ill-posed task of monocular dynamic reconstruction, the Gaussians tend to overfit the constantly changing regions such as clothes wrinkles or shadows since these regions cannot provide consistent supervision, resulting in noisy geometry and abrupt deformation that typically fail to generalize under novel views and poses.To address these limitations, we present SAGA,i.e.,Surface-Aligned Gaussian Avatar,which aligns the Gaussians with a mesh to enforce well-defined geometry and consistent deformation, thereby improving generalization under novel views and poses. Unlike existing strict alignment methods that suffer from limited expressive power and low realism,SAGA employs a two-stage alignment strategy where the Gaussians are first adhered on while then detached from the mesh, thus facilitating both good geometry and high expressivity. In the Adhered Stage, we improve the flexibility of Adhered-on-Mesh Gaussians by allowing them to flow on the mesh, in contrast to existing methods that rigidly bind Gaussians to fixed location. In the second Detached Stage, we introduce a Gaussian-Mesh Alignment regularization, which allows us to unleash the expressivity by detaching the Gaussians but maintain the geometric alignment by minimizing their location and orientation offsets from the bound triangles. Finally, since the Gaussians may drift outside the bound triangles during optimization, an efficient Walking-on-Mesh strategy is proposed to dynamically update the bound triangles.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
