Log In Sign Up

Learned convex regularizers for inverse problems

by   Subhadip Mukherjee, et al.

We consider the variational reconstruction framework for inverse problems and propose to learn a data-adaptive input-convex neural network (ICNN) as the regularization functional. The ICNN-based convex regularizer is trained adversarially to discern ground-truth images from unregularized reconstructions. Convexity of the regularizer is attractive since (i) one can establish analytical convergence guarantees for the corresponding variational reconstruction problem and (ii) devise efficient and provable algorithms for reconstruction. In particular, we show that the optimal solution to the variational problem converges to the ground-truth if the penalty parameter decays sub-linearly with respect to the norm of the noise. Further, we prove the existence of a subgradient-based algorithm that leads to monotonically decreasing error in the parameter space with iterations. To demonstrate the performance of our approach for solving inverse problems, we consider the tasks of deblurring natural images and reconstructing images in computed tomography (CT), and show that the proposed convex regularizer is at least competitive with and sometimes superior to state-of-the-art data-driven techniques for inverse problems.


page 6

page 7

page 9


Adversarial Regularizers in Inverse Problems

Inverse Problems in medical imaging and computer vision are traditionall...

Learning convex regularizers satisfying the variational source condition for inverse problems

Variational regularization has remained one of the most successful appro...

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

We propose an unsupervised approach for learning end-to-end reconstructi...

Compressed Sensing MRI Reconstruction Regularized by VAEs with Structured Image Covariance

Learned regularization for MRI reconstruction can provide complex data-d...

Uniformly convex neural networks and non-stationary iterated network Tikhonov (iNETT) method

We propose a non-stationary iterated network Tikhonov (iNETT) method for...

Variational based Mixed Noise Removal with CNN Deep Learning Regularization

In this paper, the traditional model based variational method and learni...

A Neural-Network-Based Convex Regularizer for Image Reconstruction

The emergence of deep-learning-based methods for solving inverse problem...