# Extreme Channel Prior Embedded Network for Dynamic Scene Deblurring

## TL;DR

This paper introduces ECPeNet, a novel neural network for dynamic scene deblurring that embeds extreme channel priors and utilizes a multi-scale architecture to improve deblurring performance.

## Contribution

The paper proposes a new trainable layer embedding extreme channel priors into a deblurring network, enhancing effectiveness over existing methods.

## Key findings

- ECPeNet outperforms state-of-the-art methods on GoPro and Kohler datasets.
- The embedded layer effectively integrates extreme channel priors with image features.
- Multi-scale architecture improves information flow and deblurring quality.

## Abstract

Recent years have witnessed the significant progress on convolutional neural networks (CNNs) in dynamic scene deblurring. While CNN models are generally learned by the reconstruction loss defined on training data, incorporating suitable image priors as well as regularization terms into the network architecture could boost the deblurring performance. In this work, we propose an Extreme Channel Prior embedded Network (ECPeNet) to plug the extreme channel priors (i.e., priors on dark and bright channels) into a network architecture for effective dynamic scene deblurring. A novel trainable extreme channel prior embedded layer (ECPeL) is developed to aggregate both extreme channel and blurry image representations, and sparse regularization is introduced to regularize the ECPeNet model learning. Furthermore, we present an effective multi-scale network architecture that works in both coarse-to-fine and fine-to-coarse manners for better exploiting information flow across scales. Experimental results on GoPro and Kohler datasets show that our proposed ECPeNet performs favorably against state-of-the-art deep image deblurring methods in terms of both quantitative metrics and visual quality.