Adversarially learned iterative reconstruction for imaging inverse problems

03/30/2021
by   Subhadip Mukherjee, et al.
0

In numerous practical applications, especially in medical image reconstruction, it is often infeasible to obtain a large ensemble of ground-truth/measurement pairs for supervised learning. Therefore, it is imperative to develop unsupervised learning protocols that are competitive with supervised approaches in performance. Motivated by the maximum-likelihood principle, we propose an unsupervised learning framework for solving ill-posed inverse problems. Instead of seeking pixel-wise proximity between the reconstructed and the ground-truth images, the proposed approach learns an iterative reconstruction network whose output matches the ground-truth in distribution. Considering tomographic reconstruction as an application, we demonstrate that the proposed unsupervised approach not only performs on par with its supervised variant in terms of objective quality measures but also successfully circumvents the issue of over-smoothing that supervised approaches tend to suffer from. The improvement in reconstruction quality comes at the expense of higher training complexity, but, once trained, the reconstruction time remains the same as its supervised counterpart.

READ FULL TEXT

page 9

page 11

research
07/06/2021

Unsupervised Knowledge-Transfer for Learned Image Reconstruction

Deep learning-based image reconstruction approaches have demonstrated im...
research
03/21/2023

Image Reconstruction without Explicit Priors

We consider solving ill-posed imaging inverse problems without access to...
research
06/07/2021

End-to-end reconstruction meets data-driven regularization for inverse problems

We propose an unsupervised approach for learning end-to-end reconstructi...
research
05/29/2018

Deep Mesh Projectors for Inverse Problems

We develop a new learning-based approach to ill-posed inverse problems. ...
research
05/12/2020

Deep Learning Techniques for Inverse Problems in Imaging

Recent work in machine learning shows that deep neural networks can be u...
research
03/20/2023

Unsupervised Intrinsic Image Decomposition with LiDAR Intensity

Intrinsic image decomposition (IID) is the task that decomposes a natura...
research
05/17/2021

Unsupervised Deep Learning Methods for Biological Image Reconstruction

Recently, deep learning approaches have become the main research frontie...

Please sign up or login with your details

Forgot password? Click here to reset