# Quantifying Sources of Uncertainty in Deep Learning-Based Image Reconstruction

arXiv: https://arxiv.org/abs/2011.08413 · HTML: https://mlsanity.com/paper/2011.08413/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Nov 2020.

## Built on by (most cited first, 6 of 6)

- [Conditional Variational Autoencoder for Learned Image Reconstruction](https://mlsanity.com/paper/2110.11681/) (2021)
- [Unsupervised Knowledge-Transfer for Learned Image Reconstruction](https://mlsanity.com/paper/2107.02572/) (2021)
- [Graph Structure Learning with Interpretable Bayesian Neural Networks](https://mlsanity.com/paper/2406.14786/) (2024)
- [Uncertainty Estimation and Out-of-Distribution Detection for Deep Learning-Based Image Reconstruction using the Local Lipschitz](https://mlsanity.com/paper/2305.07618/) (2023)
- [On the Quantification of Image Reconstruction Uncertainty without Training Data](https://mlsanity.com/paper/2311.09639/) (2023)
- [OCSplats: Observation Completeness Quantification and Label Noise Separation in 3DGS](https://mlsanity.com/paper/2508.01239/) (2025)

## Abstract (arXiv)

Image reconstruction methods based on deep neural networks have shown outstanding performance, equalling or exceeding the state-of-the-art results of conventional approaches, but often do not provide uncertainty information about the reconstruction. In this work we propose a scalable and efficient framework to simultaneously quantify aleatoric and epistemic uncertainties in learned iterative image reconstruction. We build on a Bayesian deep gradient descent method for quantifying epistemic uncertainty, and incorporate the heteroscedastic variance of the noise to account for the aleatoric uncertainty. We show that our method exhibits competitive performance against conventional benchmarks for computed tomography with both sparse view and limited angle data. The estimated uncertainty captures the variability in the reconstructions, caused by the restricted measurement model, and by missing information, due to the limited angle geometry.