TagSplat: Topology-Aware Gaussian Splatting for Dynamic Mesh Modeling and Tracking
This addresses a specific challenge in 4D reconstruction for animation and editing, but appears incremental as it builds on Gaussian Splatting with topology-aware modifications.
The paper tackles the problem of generating high-quality topology-consistent dynamic mesh sequences for applications like animation and model editing, achieving significantly higher accuracy than existing methods and enabling precise 3D keypoint tracking.
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/