TagSplat: Topology-Aware Gaussian Splatting for Dynamic Mesh Modeling and Tracking

TL;DR

This paper introduces TagSplat, a Gaussian Splatting-based framework that ensures topology consistency in dynamic mesh reconstruction, leading to higher accuracy and better 3D keypoint tracking.

Contribution

We propose a topology-aware dynamic reconstruction method with a Gaussian topological structure and temporal regularization, improving mesh quality and topological coherence over time.

Findings

Reconstructs topology-consistent mesh sequences with higher accuracy.

Enables precise 3D keypoint tracking.

Outperforms existing methods in mesh quality and consistency.

Abstract

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. Project page: https://haza628.github.io/tagSplat/