Image Restoration using Total Variation Regularized Deep Image Prior
This work addresses image restoration for computer vision applications, but it is incremental as it extends an existing method with a traditional regularizer.
The paper tackled image restoration by combining the deep image prior framework with total variation regularization, achieving considerable performance gains in tasks like denoising and deblurring.
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.