3D representation is essential to the significant advance of 3D generation
with 2D diffusion priors. As a flexible representation, NeRF has been first
adopted for 3D representation. With density-based volumetric rendering, it
however suffers both intensive computational overhead and inaccurate mesh
extraction. Using a signed distance field and Marching Tetrahedra, DMTet allows
for precise mesh extraction and real-time rendering but is limited in handling
large topological changes in meshes, leading to optimization challenges.
Alternatively, 3D Gaussian Splatting (3DGS) is favored in both training and
rendering efficiency while falling short in mesh extraction. In this work, we
introduce a novel 3D representation, Tetrahedron Splatting (TeT-Splatting),
that supports easy convergence during optimization, precise mesh extraction,
and real-time rendering simultaneously. This is achieved by integrating
surface-based volumetric rendering within a structured tetrahedral grid while
preserving the desired ability of precise mesh extraction, and a tile-based
differentiable tetrahedron rasterizer. Furthermore, we incorporate eikonal and
normal consistency regularization terms for the signed distance field to
improve generation quality and stability. Critically, our representation can be
trained without mesh extraction, making the optimization process easier to
converge. Our TeT-Splatting can be readily integrated in existing 3D generation
pipelines, along with polygonal mesh for texture optimization. Extensive
experiments show that our TeT-Splatting strikes a superior tradeoff among
convergence speed, render efficiency, and mesh quality as compared to previous
alternatives under varying 3D generation settings.

Tetrahedron Splatting (TeT-Splatting) is a novel 3D representation that achieves easy convergence during optimization, precise mesh extraction, and real-time rendering simultaneously, while incorporating eikonal and normal consistency regularization terms for improved generation quality and stability.