貝葉斯之光：神經輻射場的不確定性量化

Bayes' Rays: Uncertainty Quantification for Neural Radiance Fields

September 6, 2023

作者: Lily Goli, Cody Reading, Silvia Selllán, Alec Jacobson, Andrea Tagliasacchi

cs.AI

摘要

神經輻射場（Neural Radiance Fields，NeRFs）在視角合成和深度估計等應用中表現出潛力，但從多視角圖像中學習面臨固有的不確定性。目前用於量化這些不確定性的方法要麼是啟發式的，要麼是計算上要求很高的。我們引入了BayesRays，一個事後框架，用於評估任何預先訓練的NeRF中的不確定性，而無需修改訓練過程。我們的方法利用空間擾動和貝葉斯拉普拉斯近似建立體積不確定性場。我們在統計上推導了我們的算法，並展示了其在關鍵指標和應用中的優越性能。更多結果請參閱：https://bayesrays.github.io。

English

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.