TetSphere Splatting: Representing High-Quality Geometry with Lagrangian Volumetric Meshes

Abstract

We introduce TetSphere Splatting, a Lagrangian geometry representation designed for high-quality 3D shape modeling. TetSphere splatting leverages an underused yet powerful geometric primitive -- volumetric tetrahedral meshes. It represents 3D shapes by deforming a collection of tetrahedral spheres, with geometric regularizations and constraints that effectively resolve common mesh issues such as irregular triangles, non-manifoldness, and floating artifacts. Experimental results on multi-view and single-view reconstruction highlight TetSphere splatting's superior mesh quality while maintaining competitive reconstruction accuracy compared to state-of-the-art methods. Additionally, TetSphere splatting demonstrates versatility by seamlessly integrating into generative modeling tasks, such as image-to-3D and text-to-3D generation.

Cite

Text

Guo et al. "TetSphere Splatting: Representing High-Quality Geometry with Lagrangian Volumetric Meshes." International Conference on Learning Representations, 2025.

Markdown

[Guo et al. "TetSphere Splatting: Representing High-Quality Geometry with Lagrangian Volumetric Meshes." International Conference on Learning Representations, 2025.](https://mlanthology.org/iclr/2025/guo2025iclr-tetsphere/)

BibTeX

@inproceedings{guo2025iclr-tetsphere,
  title     = {{TetSphere Splatting: Representing High-Quality Geometry with Lagrangian Volumetric Meshes}},
  author    = {Guo, Minghao and Wang, Bohan and He, Kaiming and Matusik, Wojciech},
  booktitle = {International Conference on Learning Representations},
  year      = {2025},
  url       = {https://mlanthology.org/iclr/2025/guo2025iclr-tetsphere/}
}