TagSplat：面向动态网格建模与跟踪的拓扑感知高斯泼溅
TagSplat: Topology-Aware Gaussian Splatting for Dynamic Mesh Modeling and Tracking
把高斯球的连通性显式编码成拓扑结构，并据此做致密化与剪枝，可让基于高斯泼溅的动态重建直接产出流形一致的网格序列；这套「拓扑感知致密化/剪枝 + 时序正则化」的思路可迁移到任何需要从高斯表示提取干净网格或做表面跟踪的 4D 重建流程。
原文依据 We introduce a Gaussian topological structure that explicitly encodes spatial connectivity.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论拓扑一致的动态模型序列对动画与模型编辑等应用至关重要。然而，现有 4D 重建方法在生成高质量的拓扑一致网格方面仍面临挑战。为此，我们提出了一种基于高斯泼溅的拓扑感知动态重建框架。我们引入一种高斯拓扑结构，显式编码空间连通性。该结构使拓扑感知的致密化与剪枝成为可能，从而保持高斯表示的流形一致性。时序正则化项进一步保证拓扑在时间上的连贯性，而可微网格光栅化则提升了网格质量。实验结果表明，本方法重建出的拓扑一致网格序列在精度上显著优于现有方法。此外，所得网格还能支持精确的 3D 关键点跟踪。
英文原文摘要 925 字符
Topology-consistent dynamic model sequences are essential for applications such as animation and model editing. However, existing 4D reconstruction methods face challenges in generating high-quality topology-consistent meshes. To address this, we propose a topology-aware dynamic reconstruction framework based on Gaussian Splatting. We introduce a Gaussian topological structure that explicitly encodes spatial connectivity. This structure enables topology-aware densification and pruning, preserving the manifold consistency of the Gaussian representation. Temporal regularization terms further ensure topological coherence over time, while differentiable mesh rasterization improves mesh quality. Experimental results demonstrate that our method reconstructs topology-consistent mesh sequences with significantly higher accuracy than existing approaches. Moreover, the resulting meshes enable precise 3D keypoint tracking.