Tetra-NeRF: Representing Neural Radiance Fields Using Tetrahedra

TL;DR

Tetra-NeRF introduces an adaptive tetrahedral scene representation for neural radiance fields, leveraging Delaunay triangulation to improve detail and performance in novel view synthesis and 3D reconstruction.

Contribution

It proposes a novel tetrahedral-based scene representation for NeRFs, improving efficiency and detail over traditional voxel and point-based methods.

Findings

Achieves state-of-the-art results in view synthesis and 3D reconstruction.

Provides more scene detail near surfaces compared to voxel-based methods.

Outperforms point-based representations in accuracy and efficiency.

Abstract

Neural Radiance Fields (NeRFs) are a very recent and very popular approach for the problems of novel view synthesis and 3D reconstruction. A popular scene representation used by NeRFs is to combine a uniform, voxel-based subdivision of the scene with an MLP. Based on the observation that a (sparse) point cloud of the scene is often available, this paper proposes to use an adaptive representation based on tetrahedra obtained by Delaunay triangulation instead of uniform subdivision or point-based representations. We show that such a representation enables efficient training and leads to state-of-the-art results. Our approach elegantly combines concepts from 3D geometry processing, triangle-based rendering, and modern neural radiance fields. Compared to voxel-based representations, ours provides more detail around parts of the scene likely to be close to the surface. Compared to point-based representations, our approach achieves better performance. The source code is publicly available at: https://jkulhanek.com/tetra-nerf.