Deep learning

Pattern recognition (psychology)

Noise reduction

Image (mathematics)

Image restoration

Artificial intelligence

Total variation denoising

Regularization (linguistics)

Deblurring

Image denoising

Computer science

Computer vision

Convolutional neural network

Image processing

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.

Image Restoration Using Total Variation Regularized Deep Image Prior