Stochastic Neural Radiance Fields: Quantifying uncertainty in implicit 3D representations

Conference Article


International Conference on 3D Vision (3DV)





Doc link


Download the digital copy of the doc pdf document


Neural Radiance Fields (NeRF) has become a popular framework for learning implicit 3D representations and addressing different tasks such as novel-view synthesis or depth-map estimation. However, in downstream applications where decisions need to be made based on automatic predictions, it is critical to leverage the confidence associated with the model estimations. Whereas uncertainty quantification is a long-standing problem in Machine Learning, it has been largely overlooked in the recent NeRF literature. In this context, we propose Stochastic Neural Radiance Fields (S-NeRF), a generalization of standard NeRF that learns a probability distribution over all the possible radiance fields modeling the scene. This distribution allows to quantify the uncertainty associated with the scene information provided by the model. S-NeRF optimization is posed as a Bayesian learning problem that is efficiently addressed using the Variational Inference framework. Exhaustive experiments over benchmark datasets demonstrate that S-NeRF is able to provide more reliable predictions and confidence values than generic approaches previously proposed for uncertainty estimation in other domains.


computer vision.

Author keywords

Neural Radiance Fields, Bayesian learning

Scientific reference

J. Shen, A. Ruiz, A. Agudo and F. Moreno-Noguer. Stochastic Neural Radiance Fields: Quantifying uncertainty in implicit 3D representations, 2021 International Conference on 3D Vision, 2021, London, UK (Virtual), pp. 972-981.