Plenoxels: Radiance Fields Without Neural Networks

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

Cite

Text

Fridovich-Keil et al. "Plenoxels: Radiance Fields Without Neural Networks." Conference on Computer Vision and Pattern Recognition, 2022. doi:10.1109/CVPR52688.2022.00542

Markdown

[Fridovich-Keil et al. "Plenoxels: Radiance Fields Without Neural Networks." Conference on Computer Vision and Pattern Recognition, 2022.](https://mlanthology.org/cvpr/2022/fridovichkeil2022cvpr-plenoxels/) doi:10.1109/CVPR52688.2022.00542

BibTeX

@inproceedings{fridovichkeil2022cvpr-plenoxels,
  title     = {{Plenoxels: Radiance Fields Without Neural Networks}},
  author    = {Fridovich-Keil, Sara and Yu, Alex and Tancik, Matthew and Chen, Qinhong and Recht, Benjamin and Kanazawa, Angjoo},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2022},
  pages     = {5501-5510},
  doi       = {10.1109/CVPR52688.2022.00542},
  url       = {https://mlanthology.org/cvpr/2022/fridovichkeil2022cvpr-plenoxels/}
}