Tessellation GS：基于神经网格高斯的鲁棒单目动态物体重建
Tessellation GS: Neural Mesh Gaussians for Robust Monocular Reconstruction of Dynamic Objects
AI总结：
Tessellation GS通过基于网格面的神经高斯方法实现单目动态物体的鲁棒重建，显著提升了稀疏视角和动态场景下的重建性能。
摘要：
3D高斯点划法（GS）能够从姿态图像序列中实现高度逼真的场景重建，但因其各向异性特性，在视角外推时面临困难，导致过拟合和泛化能力差，特别是在稀疏视角和动态场景重建中。我们提出了Tessellation GS，一种基于网格面的结构化2D GS方法，用于从单个连续移动或静态摄像机中重建动态场景。我们的方法将2D高斯限制在局部区域，并通过在网格面上的层次神经特征推断其属性。高斯细分由一种基于细节感知损失函数的自适应面细分策略引导。此外，我们利用重建基础模型的先验知识来初始化高斯变形，使单个静态摄像机能够稳健地重建一般动态物体，这在基于优化的方法中曾极其具有挑战性。我们的方法在外观和网格重建任务上优于先前的SOTA方法，将LPIPS减少了29.1%，将Chamfer距离减少了49.2%。
英文摘要：
3D Gaussian Splatting (GS) enables highly photorealistic scene reconstruction from posed image sequences but struggles with viewpoint extrapolation due to its anisotropic nature, leading to overfitting and poor generalization, particularly in sparse-view and dynamic scene reconstruction. We propose Tessellation GS, a structured 2D GS approach anchored on mesh faces, to reconstruct dynamic scenes from a single continuously moving or static camera. Our method constrains 2D Gaussians to localized regions and infers their attributes via hierarchical neural features on mesh faces. Gaussian subdivision is guided by an adaptive face subdivision strategy driven by a detail-aware loss function. Additionally, we leverage priors from a reconstruction foundation model to initialize Gaussian deformations, enabling robust reconstruction of general dynamic objects from a single static camera, previously extremely challenging for optimization-based methods. Our method outperforms previous SOTA method, reducing LPIPS by 29.1% and Chamfer distance by 49.2% on appearance and mesh reconstruction tasks.
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。
