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

2025-12-01

AI Summary

Existing 4D reconstruction methods struggle to simultaneously achieve geometric accuracy and topological consistency, limiting the applicability of dynamic meshes in animation and editing. To address this, we propose a topology-aware Gaussian lattice framework: it explicitly models spatial connectivity among Gaussian distributions to construct a differentiable, manifold-preserving representation; introduces topology-aware densification and pruning strategies; and incorporates temporal regularization to enforce inter-frame topological stability. End-to-end optimization is enabled via differentiable mesh rasterization. Our method significantly improves topological consistency in dynamic mesh reconstruction—achieving an average 12.7% gain over state-of-the-art methods—while also enabling high-fidelity 3D keypoint tracking with a 23.4% reduction in tracking error. This provides a robust and controllable foundation for dynamic modeling and editing.

Technology Category

• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Computer Vision: Motion & Tracking
• Machine Learning: Learning with Manifolds

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

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/

Problem

• Reconstructs topology-consistent dynamic mesh sequences
• Improves mesh quality via differentiable rasterization
• Enables precise 3D keypoint tracking on meshes

Innovation

• Topology-aware Gaussian Splatting for dynamic reconstruction
• Gaussian topological structure encodes spatial connectivity
• Temporal regularization ensures topological coherence over time