TagSplat: Topology-Aware Gaussian Splatting for Dynamic Mesh Modeling and Tracking
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917116051980288 |
|---|---|
| author | Guo, Hanzhi Weng, Dongdong Su, Mo Chen, Yixiao Dongye, Xiaonuo Xu, Chenyu |
| author_facet | Guo, Hanzhi Weng, Dongdong Su, Mo Chen, Yixiao Dongye, Xiaonuo Xu, Chenyu |
| contents | 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/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_01329 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TagSplat: Topology-Aware Gaussian Splatting for Dynamic Mesh Modeling and Tracking Guo, Hanzhi Weng, Dongdong Su, Mo Chen, Yixiao Dongye, Xiaonuo Xu, Chenyu Graphics Computer Vision and Pattern Recognition 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/ |
| title | TagSplat: Topology-Aware Gaussian Splatting for Dynamic Mesh Modeling and Tracking |
| topic | Graphics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.01329 |