# Integrating neural networks into the blind deblurring framework to compete with the end-to-end learning-based methods

## TL;DR

This paper proposes a hybrid blind deblurring approach that combines neural networks with traditional methods, improving detail restoration and generalization over pure deep learning models.

## Contribution

It introduces a novel integration of CNNs into the deblurring framework, specifically with SEN and RP-GAN, to address limitations of end-to-end neural methods.

## Key findings

- Outperforms state-of-the-art end-to-end methods in detail restoration.
- Shows better generalization to complex motion blur.
- Restores more reasonable image details.

## Abstract

Recently, end-to-end learning-based methods based on deep neural network (DNN) have been proven effective for blind deblurring. Without human-made assumptions and numerical algorithms, they are able to restore images with fewer artifacts and better perceptual quality. However, in practice, we also find some of their drawbacks. Without the theoretical guidance, these methods can not perform well when the motion is complex and sometimes generate unreasonable results. In this paper, for overcoming these drawbacks, we integrate deep convolution neural networks into conventional deblurring framework. Specifically, we build Stacked Estimation Residual Net (SEN) to estimate the motion flow map and Recurrent Prior Generative and Adversarial Net (RP-GAN) to learn the implicit image prior in the optimization model. Comparing with state-of-the-art end-to-end learning-based methods, our method restores reasonable details and shows better generalization ability.