Work

Image Restoration Using Total Variation Regularized Deep Image Prior

Year: 2019
Type: conference-paper
Abstract: In the past decade, sparsity-driven regularization has led to significant improvements in image reconstruction. Traditional regularizers, such as total variation (TV), rely on analytical models of sparsity. However, increasingly the field is moving towards trainable models, inspired from deep learning. Deep image prior (DIP) is a recent regularization framework that uses a convolutional neural network (CNN) architecture without data-driven training. This paper extends the DIP framework by combining it with the traditional TV regularization. We show that the inclusion of TV leads to considerable performance gains when tested on several traditional restoration tasks such as image denoising and deblurring.
Language: English
Open Access status: green
OpenAlex ID: W2963426457
FWCI: 6.951
Cites: 32
Cited by: 268
Related to: 10