Adversarial Regularizers in Inverse Problems

Abstract

Inverse Problems in medical imaging and computer vision are traditionally solved using purely model-based methods. Among those variational regularization models are one of the most popular approaches. We propose a new framework for applying data-driven approaches to inverse problems, using a neural network as a regularization functional. The network learns to discriminate between the distribution of ground truth images and the distribution of unregularized reconstructions. Once trained, the network is applied to the inverse problem by solving the corresponding variational problem. Unlike other data-based approaches for inverse problems, the algorithm can be applied even if only unsupervised training data is available. Experiments demonstrate the potential of the framework for denoising on the BSDS dataset and for computed tomography reconstruction on the LIDC dataset.

published at NeurIPS 2018

References in corpus (1)

• Deep Convolutional Neural Network for Inverse Problems in Imaging

Cited by in corpus (12)

• The Modern Mathematics of Deep Learning
• Three-dimensional deep learning-based reduced order model for unsteady flow dynamics with variable Reynolds number
• PatchNR: Learning from Very Few Images by Patch Normalizing Flow Regularization
• Data driven regularization by projection
• Adaptive Tikhonov strategies for stochastic ensemble Kalman inversion
• SPRING: A fast stochastic proximal alternating method for non-smooth non-convex optimization
• Uniformly convex neural networks and non-stationary iterated network Tikhonov (iNETT) method
• Semi-Blind Source Separation with Learned Constraints
• GAN2GAN: Generative Noise Learning for Blind Denoising with Single Noisy Images
• Invertible residual networks in the context of regularization theory for linear inverse problems
• Random mesh projectors for inverse problems
• TAEN: A Model-Constrained Tikhonov Autoencoder Network for Forward and Inverse Problems