Bayes' Rays: Uncertainty Quantification for Neural Radiance Fields

Lily Goli, Cody Reading, Silvia Sellán, Alec Jacobson, Andrea Tagliasacchi
2/14/2026

No official code found. Best implementation: BayesRays/BayesRays (157 stars, MIT, last commit 2024-02-29).

Abstract

Neural Radiance Fields (NeRFs) have shown promise in applications like view synthesis and depth estimation, but learning from multiview images faces inherent uncertain-ties. Current methods to quantify them are either heuristic or computationally demanding. We introduce Bayes'Rays, 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 spa-tial perturbations and a Bayesian Laplace approximation. We derive our algorithm statistically and show its superior performance in key metrics and applications. More results available at: https://bayesrays.github.io

View on arXivView PDF

Code Implementations(1)

BayesRays/BayesRaysCommunity100%
MIT

Official Code for Bayes' Rays Paper

15714PythonSep 12, 20232 years agoMIT

Similar Papers

Modeling uncertainty for Gaussian Splatting

86% match2024

Uncertainty-Aware Normal-Guided Gaussian Splatting for Surface Reconstruction from Sparse Image Sequences

84% match1 repo82025

Make Me a BNN: A Simple Strategy for Estimating Bayesian Uncertainty from Pre-trained Models

84% match1 repo72026

Revisiting Gradient-based Uncertainty for Monocular Depth Estimation

84% match1 repo562025

Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting

83% match1 repo1742026

Bayesian NeRF: Quantifying Uncertainty with Volume Density for Neural Implicit Fields

82% match1 repo172024

Cite this paper

@article{goli2026bayes,
  title  = {Bayes' Rays: Uncertainty Quantification for Neural Radiance Fields},
  author = {Lily Goli and Cody Reading and Silvia Sellán and Alec Jacobson and Andrea Tagliasacchi},
  year   = {2026},
  eprint = {2309.03185},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/pdf/2309.03185},
  journal = {CVPR 2023 2023}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2309.03185.svg)](https://codeofpaper.com/paper/2309.03185)

Discussion