Bayes' Rays: Uncertainty Quantification for Neural Radiance Fields
This addresses uncertainty quantification for NeRF users, offering a more efficient alternative to existing methods, though it is incremental as it builds on prior NeRF work.
The paper tackles the problem of quantifying uncertainty in Neural Radiance Fields (NeRFs) for tasks like view synthesis and depth estimation, introducing BayesRays as a post-hoc framework that achieves superior performance in key metrics without modifying training.
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 pre-trained 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.