Plenoxels: Radiance Fields without Neural Networks

We introduce Plenoxels (plenoptic voxels), a system for photorealistic view synthesis. Plenoxels represent a scene as a sparse 3D grid with spherical harmonics. This representation can be optimized from calibrated images via gradient methods and regularization without any neural components. On standard, benchmark tasks, Plenoxels are optimized two orders of magnitude faster than Neural Radiance Fields with no loss in visual quality. For video and code, please see https://alexyu.net/plenoxels.

Automated summary

We introduce Plenoxels, a system for photorealistic view synthesis using a sparse 3D grid representation with spherical harmonics. This representation can be optimized without neural components and achieves a two orders of magnitude faster speed compared to Neural Radiance Fields on benchmark tasks while maintaining visual quality.