English

Plenoxels: Radiance Fields without Neural Networks

Computer Vision and Pattern Recognition 2021-12-10 v1 Graphics

Abstract

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.

Keywords

Cite

@article{arxiv.2112.05131,
  title  = {Plenoxels: Radiance Fields without Neural Networks},
  author = {Alex Yu and Sara Fridovich-Keil and Matthew Tancik and Qinhong Chen and Benjamin Recht and Angjoo Kanazawa},
  journal= {arXiv preprint arXiv:2112.05131},
  year   = {2021}
}

Comments

For video and code, please see https://alexyu.net/plenoxels

R2 v1 2026-06-24T08:11:18.354Z