Combining Weighted Total Variation and Deep Image Prior for natural and medical image restoration via ADMM

Abstract

In the last decades, unsupervised deep learning based methods have caught researchers attention, since in many real applications, such as medical imaging, collecting a great amount of training examples is not always feasible. Moreover, the construction of a good training set is time consuming and hard because the selected data have to be enough representative for the task. In this paper, we focus on the Deep Image Prior (DIP) framework and we propose to combine it with a space-variant Total Variation regularizer with an automatic estimation of the local regularization parameters. Differently from other existing approaches, we solve the arising minimization problem via the flexible Alternating Direction Method of Multipliers (ADMM). Furthermore, we provide a specific implementation also for the standard isotropic Total Variation. The promising performances of the proposed approach, in terms of PSNR and SSIM values, are addressed through several experiments on simulated as well as real natural and medical corrupted images.

arXiv commentconference paper

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• A Review of Convolutional Neural Networks for Inverse Problems in Imaging
• Computed Tomography Reconstruction Using Deep Image Prior and Learned Reconstruction Methods
• Compressed Sensing with Deep Image Prior and Learned Regularization
• Regularization by architecture: A deep prior approach for inverse problems
• Uniform Penalty inversion of two-dimensional NMR Relaxation data
• Adaptive parameter selection for weighted-TV image reconstruction problems

Cited by in corpus (3)

• Self-Supervised Nonlinear Transform-Based Tensor Nuclear Norm for Multi-Dimensional Image Recovery
• Unsupervised Knowledge-Transfer for Learned Image Reconstruction
• Deep image prior inpainting of ancient frescoes in the Mediterranean Alpine arc