Plenoxels: Radiance Fields without Neural Networks
This provides a faster alternative for view synthesis tasks, though it is incremental as it builds on existing radiance field concepts.
They tackled photorealistic view synthesis by representing scenes as a sparse 3D grid with spherical harmonics, achieving optimization two orders of magnitude faster than Neural Radiance Fields without loss in visual quality.
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.