Tetra-NeRF: Representing Neural Radiance Fields Using Tetrahedra
This work addresses the challenge of efficient and detailed scene representation for neural radiance fields, offering an incremental improvement over existing methods by combining geometry processing with neural rendering.
The paper tackles the problem of novel view synthesis and 3D reconstruction by proposing Tetra-NeRF, which uses an adaptive tetrahedral representation based on Delaunay triangulation instead of uniform voxels or point clouds, leading to state-of-the-art results with more detail near surfaces and better performance than point-based methods.
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.