Conditional Variational Autoencoder for Learned Image Reconstruction

by   Chen Zhang, et al.

Learned image reconstruction techniques using deep neural networks have recently gained popularity, and have delivered promising empirical results. However, most approaches focus on one single recovery for each observation, and thus neglect the uncertainty information. In this work, we develop a novel computational framework that approximates the posterior distribution of the unknown image at each query observation. The proposed framework is very flexible: It handles implicit noise models and priors, it incorporates the data formation process (i.e., the forward operator), and the learned reconstructive properties are transferable between different datasets. Once the network is trained using the conditional variational autoencoder loss, it provides a computationally efficient sampler for the approximate posterior distribution via feed-forward propagation, and the summarizing statistics of the generated samples are used for both point-estimation and uncertainty quantification. We illustrate the proposed framework with extensive numerical experiments on positron emission tomography (with both moderate and low count levels) showing that the framework generates high-quality samples when compared with state-of-the-art methods.



There are no comments yet.


page 13

page 15

page 16

page 17

page 18


Deep Probabilistic Imaging: Uncertainty Quantification and Multi-modal Solution Characterization for Computational Imaging

Computational image reconstruction algorithms generally produce a single...

Unsupervised Knowledge-Transfer for Learned Image Reconstruction

Deep learning-based image reconstruction approaches have demonstrated im...

Spatially-Adaptive Reconstruction in Computed Tomography using Neural Networks

We propose a supervised machine learning approach for boosting existing ...

Improved low-count quantitative PET reconstruction with a variational neural network

Image reconstruction in low-count PET is particularly challenging becaus...

Bayesian Imaging With Data-Driven Priors Encoded by Neural Networks: Theory, Methods, and Algorithms

This paper proposes a new methodology for performing Bayesian inference ...

Synthetic Aperture Radar Image Formation with Uncertainty Quantification

Synthetic aperture radar (SAR) is a day or night any-weather imaging mod...

CosmoVAE: Variational Autoencoder for CMB Image Inpainting

Cosmic microwave background radiation (CMB) is critical to the understan...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.