Bayes' Rays: Uncertainty Quantification for Neural Radiance Fields
Abstract
Neural Radiance Fields (NeRFs) have shown promise in applications like view synthesis and depth estimation but learning from multiview images faces inherent uncertainties. Current methods to quantify them are either heuristic or computationally demanding. We introduce BayesRays a post-hoc framework to evaluate uncertainty in any pretrained NeRF without modifying the training process. Our method establishes a volumetric uncertainty field using spatial perturbations and a Bayesian Laplace approximation. We derive our algorithm statistically and show its superior performance in key metrics and applications. Additional results available at: https://bayesrays.github.io/
Cite
Text
Goli et al. "Bayes' Rays: Uncertainty Quantification for Neural Radiance Fields." Conference on Computer Vision and Pattern Recognition, 2024.Markdown
[Goli et al. "Bayes' Rays: Uncertainty Quantification for Neural Radiance Fields." Conference on Computer Vision and Pattern Recognition, 2024.](https://mlanthology.org/cvpr/2024/goli2024cvpr-bayes/)BibTeX
@inproceedings{goli2024cvpr-bayes,
title = {{Bayes' Rays: Uncertainty Quantification for Neural Radiance Fields}},
author = {Goli, Lily and Reading, Cody and Sellán, Silvia and Jacobson, Alec and Tagliasacchi, Andrea},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2024},
pages = {20061-20070},
url = {https://mlanthology.org/cvpr/2024/goli2024cvpr-bayes/}
}