Radiant Triangle Soup with Soft Connectivity Forces for 3D Reconstruction and Novel View Synthesis

In this work, we introduce an inference-time optimization framework utilizing triangles to represent the geometry and appearance of the scene. More specifically, we develop a scene optimization algorithm for triangle soup, a collection of disconnected semi-transparent triangle primitives. Compared to the current most-widely used primitives for 3D scene representation, namely Gaussian splats, triangles allow for more expressive color interpolation, and benefit from a large algorithmic infrastructure for downstream tasks. Triangles, unlike full-rank Gaussian kernels, naturally combine to form surfaces. We formulate connectivity forces between triangles during optimization, encouraging explicit, but soft, surface continuity in 3D. We perform experiments on a representative 3D reconstruction dataset and show competitive photometric and geometric results.

@article{burgdorfer2025_2505.23642,
  title={ Radiant Triangle Soup with Soft Connectivity Forces for 3D Reconstruction and Novel View Synthesis },
  author={ Nathaniel Burgdorfer and Philippos Mordohai },
  journal={arXiv preprint arXiv:2505.23642},
  year={ 2025 }
}