Tessellation GS: Neural Mesh Gaussians for Robust Monocular Reconstruction of Dynamic Objects
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917132842827776 |
|---|---|
| author | Tao, Shuohan Zhou, Boyao Tu, Hanzhang Wang, Yuwang Liu, Yebin |
| author_facet | Tao, Shuohan Zhou, Boyao Tu, Hanzhang Wang, Yuwang Liu, Yebin |
| contents | 3D Gaussian Splatting (GS) enables highly photorealistic scene reconstruction from posed image sequences but struggles with viewpoint extrapolation due to its anisotropic nature, leading to overfitting and poor generalization, particularly in sparse-view and dynamic scene reconstruction. We propose Tessellation GS, a structured 2D GS approach anchored on mesh faces, to reconstruct dynamic scenes from a single continuously moving or static camera. Our method constrains 2D Gaussians to localized regions and infers their attributes via hierarchical neural features on mesh faces. Gaussian subdivision is guided by an adaptive face subdivision strategy driven by a detail-aware loss function. Additionally, we leverage priors from a reconstruction foundation model to initialize Gaussian deformations, enabling robust reconstruction of general dynamic objects from a single static camera, previously extremely challenging for optimization-based methods. Our method outperforms previous SOTA method, reducing LPIPS by 29.1% and Chamfer distance by 49.2% on appearance and mesh reconstruction tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_07381 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Tessellation GS: Neural Mesh Gaussians for Robust Monocular Reconstruction of Dynamic Objects Tao, Shuohan Zhou, Boyao Tu, Hanzhang Wang, Yuwang Liu, Yebin Computer Vision and Pattern Recognition 3D Gaussian Splatting (GS) enables highly photorealistic scene reconstruction from posed image sequences but struggles with viewpoint extrapolation due to its anisotropic nature, leading to overfitting and poor generalization, particularly in sparse-view and dynamic scene reconstruction. We propose Tessellation GS, a structured 2D GS approach anchored on mesh faces, to reconstruct dynamic scenes from a single continuously moving or static camera. Our method constrains 2D Gaussians to localized regions and infers their attributes via hierarchical neural features on mesh faces. Gaussian subdivision is guided by an adaptive face subdivision strategy driven by a detail-aware loss function. Additionally, we leverage priors from a reconstruction foundation model to initialize Gaussian deformations, enabling robust reconstruction of general dynamic objects from a single static camera, previously extremely challenging for optimization-based methods. Our method outperforms previous SOTA method, reducing LPIPS by 29.1% and Chamfer distance by 49.2% on appearance and mesh reconstruction tasks. |
| title | Tessellation GS: Neural Mesh Gaussians for Robust Monocular Reconstruction of Dynamic Objects |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.07381 |