# Extreme Channel Prior Embedded Network for Dynamic Scene Deblurring

arXiv: https://arxiv.org/abs/1903.00763 · HTML: https://mlsanity.com/paper/1903.00763/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Mar 2019.

## Built on by (most cited first, 1 of 1)

- [Graph Convolutional Networks in Feature Space for Image Deblurring and Super-resolution](https://mlsanity.com/paper/2105.10465/) (2021)

## Abstract (arXiv)

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.