DeepAI AI Chat
Log In Sign Up

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.


page 13

page 15

page 16

page 17

page 18


Uncertainty Quantification for Deep Unrolling-Based Computational Imaging

Deep unrolling is an emerging deep learning-based image reconstruction m...

Unsupervised Knowledge-Transfer for Learned Image Reconstruction

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

Utilizing variational autoencoders in the Bayesian inverse problem of photoacoustic tomography

There has been an increasing interest in utilizing machine learning meth...

Spatially-Adaptive Reconstruction in Computed Tomography using Neural Networks

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

Differentiable Uncalibrated Imaging

We propose a differentiable imaging framework to address uncertainty in ...